iiif_print 1.0.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (211) hide show
  1. checksums.yaml +7 -0
  2. data/.coveralls.yml +2 -0
  3. data/.env +5 -0
  4. data/.fcrepo_wrapper +4 -0
  5. data/.github/release.yml +20 -0
  6. data/.github/workflows/branches.yml +24 -0
  7. data/.github/workflows/build-lint-test-action.yaml +33 -0
  8. data/.github/workflows/release_labels.yml +25 -0
  9. data/.gitignore +52 -0
  10. data/.rubocop.yml +177 -0
  11. data/.solr_wrapper +8 -0
  12. data/.travis.yml +49 -0
  13. data/CONTRIBUTING.md +181 -0
  14. data/Dockerfile +15 -0
  15. data/Gemfile +52 -0
  16. data/LICENSE +203 -0
  17. data/README.md +203 -0
  18. data/Rakefile +38 -0
  19. data/app/actors/iiif_print/actors/file_set_actor_decorator.rb +56 -0
  20. data/app/assets/config/iiif_print_manifest.js +2 -0
  21. data/app/assets/images/iiif_print/.keep +0 -0
  22. data/app/assets/javascripts/iiif_print/autocomplete_fix.js +33 -0
  23. data/app/assets/javascripts/iiif_print/ocr_search.js.erb +6 -0
  24. data/app/assets/javascripts/iiif_print.js +3 -0
  25. data/app/assets/stylesheets/iiif_print/_iiif_print.scss +4 -0
  26. data/app/assets/stylesheets/iiif_print/_issue_search.scss +13 -0
  27. data/app/assets/stylesheets/iiif_print/_issues_calendar.scss +18 -0
  28. data/app/assets/stylesheets/iiif_print/_newspapers_search.scss +38 -0
  29. data/app/assets/stylesheets/iiif_print/_search_results.scss +6 -0
  30. data/app/helpers/hyrax/iiif_helper.rb +22 -0
  31. data/app/helpers/iiif_print/application_helper.rb +5 -0
  32. data/app/helpers/iiif_print_helper.rb +64 -0
  33. data/app/indexers/concerns/iiif_print/child_indexer.rb +34 -0
  34. data/app/indexers/concerns/iiif_print/file_set_indexer.rb +29 -0
  35. data/app/mailers/iiif_print/application_mailer.rb +8 -0
  36. data/app/models/concerns/iiif_print/set_child_flag.rb +29 -0
  37. data/app/models/concerns/iiif_print/solr/document.rb +47 -0
  38. data/app/models/iiif_print/application_record.rb +6 -0
  39. data/app/models/iiif_print/derivative_attachment.rb +8 -0
  40. data/app/models/iiif_print/iiif_search_response_decorator.rb +17 -0
  41. data/app/models/iiif_print/ingest_file_relation.rb +14 -0
  42. data/app/models/iiif_print/pending_relationship.rb +7 -0
  43. data/app/presenters/iiif_print/iiif_manifest_presenter_behavior.rb +10 -0
  44. data/app/presenters/iiif_print/iiif_manifest_presenter_factory_behavior.rb +33 -0
  45. data/app/presenters/iiif_print/work_show_presenter_decorator.rb +29 -0
  46. data/app/renderers/hyrax/renderers/faceted_attribute_renderer_decorator.rb +18 -0
  47. data/app/search_builders/concerns/iiif_print/exclude_models.rb +17 -0
  48. data/app/search_builders/concerns/iiif_print/highlight_search_params.rb +14 -0
  49. data/app/services/iiif_print/manifest_builder_service_behavior.rb +97 -0
  50. data/app/services/iiif_print/pluggable_derivative_service.rb +120 -0
  51. data/app/views/catalog/_snippets_more.html.erb +16 -0
  52. data/app/views/hyrax/base/_representative_media.html.erb +9 -0
  53. data/app/views/hyrax/base/iiif_viewers/_universal_viewer.html.erb +8 -0
  54. data/app/views/hyrax/file_sets/_actions.html.erb +45 -0
  55. data/bin/rails +13 -0
  56. data/config/fcrepo_wrapper_test.yml +5 -0
  57. data/config/initializers/assets.rb +2 -0
  58. data/config/locales/iiif_print.de.yml +148 -0
  59. data/config/locales/iiif_print.en.yml +119 -0
  60. data/config/locales/iiif_print.es.yml +148 -0
  61. data/config/locales/iiif_print.fr.yml +149 -0
  62. data/config/locales/iiif_print.it.yml +142 -0
  63. data/config/locales/iiif_print.pt-BR.yml +148 -0
  64. data/config/locales/iiif_print.zh.yml +142 -0
  65. data/config/solr_wrapper_test.yml +9 -0
  66. data/config/test-fixture/solr-config/_rest_managed.json +3 -0
  67. data/config/test-fixture/solr-config/admin-extra.html +31 -0
  68. data/config/test-fixture/solr-config/elevate.xml +36 -0
  69. data/config/test-fixture/solr-config/mapping-ISOLatin1Accent.txt +246 -0
  70. data/config/test-fixture/solr-config/protwords.txt +21 -0
  71. data/config/test-fixture/solr-config/schema.xml +366 -0
  72. data/config/test-fixture/solr-config/scripts.conf +24 -0
  73. data/config/test-fixture/solr-config/solrconfig.xml +322 -0
  74. data/config/test-fixture/solr-config/spellings.txt +2 -0
  75. data/config/test-fixture/solr-config/stopwords.txt +58 -0
  76. data/config/test-fixture/solr-config/stopwords_en.txt +58 -0
  77. data/config/test-fixture/solr-config/synonyms.txt +31 -0
  78. data/config/test-fixture/solr-config/xslt/example.xsl +132 -0
  79. data/config/test-fixture/solr-config/xslt/example_atom.xsl +67 -0
  80. data/config/test-fixture/solr-config/xslt/example_rss.xsl +66 -0
  81. data/config/test-fixture/solr-config/xslt/luke.xsl +337 -0
  82. data/config/vendor/fits.xml +55 -0
  83. data/config/vendor/imagemagick-6-policy.xml +76 -0
  84. data/db/migrate/20181214181358_create_iiif_print_derivative_attachments.rb +12 -0
  85. data/db/migrate/20190107165909_create_iiif_print_ingest_file_relations.rb +11 -0
  86. data/db/migrate/20230109000000_create_iiif_print_pending_relationships.rb +11 -0
  87. data/docker-compose.yml +129 -0
  88. data/iiif_print.gemspec +43 -0
  89. data/lib/generators/iiif_print/assets_generator.rb +29 -0
  90. data/lib/generators/iiif_print/catalog_controller_generator.rb +32 -0
  91. data/lib/generators/iiif_print/install_generator.rb +52 -0
  92. data/lib/generators/iiif_print/templates/config/initializers/iiif_print.rb +22 -0
  93. data/lib/generators/iiif_print/templates/iiif_print.scss +1 -0
  94. data/lib/iiif_print/base_derivative_service.rb +113 -0
  95. data/lib/iiif_print/blacklight_iiif_search/annotation_decorator.rb +84 -0
  96. data/lib/iiif_print/catalog_search_builder.rb +31 -0
  97. data/lib/iiif_print/configuration.rb +99 -0
  98. data/lib/iiif_print/data/fileset_helper.rb +25 -0
  99. data/lib/iiif_print/data/path_helper.rb +40 -0
  100. data/lib/iiif_print/data/work_derivatives.rb +323 -0
  101. data/lib/iiif_print/data/work_file.rb +92 -0
  102. data/lib/iiif_print/data/work_files.rb +199 -0
  103. data/lib/iiif_print/data.rb +35 -0
  104. data/lib/iiif_print/engine.rb +77 -0
  105. data/lib/iiif_print/errors.rb +9 -0
  106. data/lib/iiif_print/image_tool.rb +119 -0
  107. data/lib/iiif_print/jobs/application_job.rb +8 -0
  108. data/lib/iiif_print/jobs/child_works_from_pdf_job.rb +107 -0
  109. data/lib/iiif_print/jobs/create_relationships_job.rb +78 -0
  110. data/lib/iiif_print/jp2_derivative_service.rb +118 -0
  111. data/lib/iiif_print/jp2_image_metadata.rb +81 -0
  112. data/lib/iiif_print/lineage_service.rb +41 -0
  113. data/lib/iiif_print/metadata.rb +125 -0
  114. data/lib/iiif_print/pdf_derivative_service.rb +42 -0
  115. data/lib/iiif_print/split_pdfs/child_work_creation_from_pdf_service.rb +75 -0
  116. data/lib/iiif_print/split_pdfs/pages_into_images_service.rb +130 -0
  117. data/lib/iiif_print/split_pdfs/pdf_image_extraction_service.rb +85 -0
  118. data/lib/iiif_print/text_extraction/alto_reader.rb +123 -0
  119. data/lib/iiif_print/text_extraction/hocr_reader.rb +172 -0
  120. data/lib/iiif_print/text_extraction/page_ocr.rb +87 -0
  121. data/lib/iiif_print/text_extraction/render_alto.rb +84 -0
  122. data/lib/iiif_print/text_extraction/word_coords_builder.rb +38 -0
  123. data/lib/iiif_print/text_extraction.rb +11 -0
  124. data/lib/iiif_print/text_extraction_derivative_service.rb +47 -0
  125. data/lib/iiif_print/text_formats_from_alto_service.rb +77 -0
  126. data/lib/iiif_print/tiff_derivative_service.rb +50 -0
  127. data/lib/iiif_print/version.rb +3 -0
  128. data/lib/iiif_print/works_controller_behavior.rb +9 -0
  129. data/lib/iiif_print.rb +136 -0
  130. data/lib/tasks/set_child_works.rake +22 -0
  131. data/spec/.keep.txt +1 -0
  132. data/spec/factories/ability.rb +6 -0
  133. data/spec/factories/newspaper_issue.rb +7 -0
  134. data/spec/factories/newspaper_page.rb +7 -0
  135. data/spec/factories/newspaper_page_solr_document.rb +12 -0
  136. data/spec/factories/newspaper_title.rb +8 -0
  137. data/spec/factories/uploaded_pdf_file.rb +9 -0
  138. data/spec/factories/uploaded_txt_file.rb +9 -0
  139. data/spec/factories/user.rb +13 -0
  140. data/spec/fixtures/files/4.1.07.jp2 +0 -0
  141. data/spec/fixtures/files/4.1.07.tiff +0 -0
  142. data/spec/fixtures/files/README.md +7 -0
  143. data/spec/fixtures/files/alto-2-0.xsd +714 -0
  144. data/spec/fixtures/files/broken-truncated.pdf +0 -0
  145. data/spec/fixtures/files/credits.md +16 -0
  146. data/spec/fixtures/files/lowres-gray-via-ndnp-sample.tiff +0 -0
  147. data/spec/fixtures/files/minimal-1-page.pdf +0 -0
  148. data/spec/fixtures/files/minimal-2-page.pdf +0 -0
  149. data/spec/fixtures/files/minimal-alto.xml +31 -0
  150. data/spec/fixtures/files/ndnp-alto-sample.xml +24 -0
  151. data/spec/fixtures/files/ndnp-sample1-json.json +1 -0
  152. data/spec/fixtures/files/ndnp-sample1-txt.txt +1 -0
  153. data/spec/fixtures/files/ndnp-sample1.pdf +0 -0
  154. data/spec/fixtures/files/ocr_alto.xml +202 -0
  155. data/spec/fixtures/files/ocr_alto_scaled_4pts_per_px.xml +202 -0
  156. data/spec/fixtures/files/ocr_color.tiff +0 -0
  157. data/spec/fixtures/files/ocr_gray.jp2 +0 -0
  158. data/spec/fixtures/files/ocr_gray.tiff +0 -0
  159. data/spec/fixtures/files/ocr_mono.tiff +0 -0
  160. data/spec/fixtures/files/ocr_mono_text_hocr.html +78 -0
  161. data/spec/fixtures/files/page1.tiff +0 -0
  162. data/spec/fixtures/files/sample-4page-issue.pdf +0 -0
  163. data/spec/fixtures/files/sample-color-newsletter.pdf +0 -0
  164. data/spec/fixtures/files/thumbnail.jpg +0 -0
  165. data/spec/helpers/hyrax/iiif_helper_spec.rb +65 -0
  166. data/spec/helpers/iiif_print_helper_spec.rb +43 -0
  167. data/spec/iiif_print/base_derivative_service_spec.rb +11 -0
  168. data/spec/iiif_print/blacklight_iiif_search/annotation_decorator_spec.rb +51 -0
  169. data/spec/iiif_print/catalog_search_builder_spec.rb +60 -0
  170. data/spec/iiif_print/configuration_spec.rb +67 -0
  171. data/spec/iiif_print/data/work_derivatives_spec.rb +245 -0
  172. data/spec/iiif_print/data/work_file_spec.rb +99 -0
  173. data/spec/iiif_print/data/work_files_spec.rb +237 -0
  174. data/spec/iiif_print/image_tool_spec.rb +109 -0
  175. data/spec/iiif_print/jobs/child_works_from_pdf_job_spec.rb +30 -0
  176. data/spec/iiif_print/jobs/create_relationships_job_spec.rb +17 -0
  177. data/spec/iiif_print/jp2_image_metadata_spec.rb +37 -0
  178. data/spec/iiif_print/lineage_service_spec.rb +13 -0
  179. data/spec/iiif_print/metadata_spec.rb +115 -0
  180. data/spec/iiif_print/split_pdfs/pages_into_images_service_spec.rb +6 -0
  181. data/spec/iiif_print/text_extraction/alto_reader_spec.rb +49 -0
  182. data/spec/iiif_print/text_extraction/hocr_reader_spec.rb +45 -0
  183. data/spec/iiif_print/text_extraction/page_ocr_spec.rb +84 -0
  184. data/spec/iiif_print/text_extraction/render_alto_spec.rb +54 -0
  185. data/spec/iiif_print/text_extraction/word_coords_builder_spec.rb +44 -0
  186. data/spec/iiif_print_spec.rb +51 -0
  187. data/spec/misc_shared.rb +111 -0
  188. data/spec/models/iiif_print/derivative_attachment_spec.rb +37 -0
  189. data/spec/models/iiif_print/ingest_file_relation_spec.rb +56 -0
  190. data/spec/models/solr_document_spec.rb +14 -0
  191. data/spec/presenters/iiif_print/iiif_manifest_presenter_behavior_spec.rb +19 -0
  192. data/spec/presenters/iiif_print/iiif_manifest_presenter_factory_behavior_spec.rb +49 -0
  193. data/spec/services/iiif_print/jp2_derivative_service_spec.rb +59 -0
  194. data/spec/services/iiif_print/pdf_derivative_service_spec.rb +66 -0
  195. data/spec/services/iiif_print/pluggable_derivative_service_spec.rb +178 -0
  196. data/spec/services/iiif_print/text_extraction_derivative_service_spec.rb +82 -0
  197. data/spec/services/iiif_print/text_formats_from_alto_service_spec.rb +127 -0
  198. data/spec/services/iiif_print/tiff_derivative_service_spec.rb +65 -0
  199. data/spec/spec_helper.rb +181 -0
  200. data/spec/support/controller_level_helpers.rb +28 -0
  201. data/spec/support/iiif_print_models.rb +127 -0
  202. data/spec/test_app_templates/blacklight.yml +9 -0
  203. data/spec/test_app_templates/fedora.yml +15 -0
  204. data/spec/test_app_templates/lib/generators/test_app_generator.rb +40 -0
  205. data/spec/test_app_templates/redis.yml +9 -0
  206. data/spec/test_app_templates/solr/conf/schema.xml +362 -0
  207. data/spec/test_app_templates/solr/conf/solrconfig.xml +322 -0
  208. data/spec/test_app_templates/solr.yml +7 -0
  209. data/tasks/iiif_print_dev.rake +34 -0
  210. data/tmp/.keep +0 -0
  211. metadata +605 -0
data/spec/fixtures/files/credits.md ADDED
@@ -0,0 +1,16 @@
1
+ ## Sample credits
2
+
3
+ * `sample-color-newsletter.pdf` — originally via:
4
+ - http://digitalpreservation.gov/news/newsletter/201306.pdf
5
+ - Re-rendered with embedded fonts via Apple Preview.app
6
+ * `ndnp-sample1.pdf` — originally via:
7
+ - https://chroniclingamerica.loc.gov/data/batches/batch_dlc_harry_ver01/data/sn82016187/00211102366/1898111001/0528.pdf
8
+ - `lowres-gray-via-ndnp-sample.tiff` based on this page image used as a
9
+ low resolution 8 bit grayscale TIFF test image in derivative testing.
10
+ - `ocr_gray.tiff`, `ocr_color.tiff`, and `ocr_gray.jp2` are all derived
11
+ from this source.
12
+ * `4.1.07.tiff` is a low-res color sample image from USC-SIPI Image Database
13
+ and is licensed as "Free to use". Via http://sipi.usc.edu/database/
14
+ - 4.1.07.jp2 is a derivative of this made via opj_compress
15
+ * `ndnp-alto-sample.xml` from NDNP Sample Content, via:
16
+ - https://chroniclingamerica.loc.gov/data/batches/batch_dlc_harry_ver01/data/sn82016187/00211102366/1898111001/0528.xml
data/spec/fixtures/files/minimal-alto.xml ADDED
@@ -0,0 +1,31 @@
1
+ <?xml version="1.0" encoding="UTF-8"?>
2
+ <alto xmlns="http://www.loc.gov/standards/alto/ns-v2#">
3
+ <!-- Minimal ALTO 2.0 (per NDNP 2018 guidelines) example should comply
4
+ with schema@ https://www.loc.gov/standards/alto/v2/alto-2-0.xsd
5
+ -->
6
+ <Description>
7
+ <MeasurementUnit>pixel</MeasurementUnit>
8
+ </Description>
9
+ <!-- no Styles element in this minimal ALTO -->
10
+ <Layout>
11
+ <Page ID="ID1" PHYSICAL_IMG_NR="1">
12
+ <!-- coordinates as float -->
13
+ <PrintSpace HEIGHT="" WIDTH="" HPOS="" VPOS="">
14
+ <!-- if we do not have block/line positioning, and only have
15
+ word coordinates, we end up with something a bit messy
16
+ treating the whole document as one big line of text to
17
+ simply comply with ALTO schema.
18
+ -->
19
+ <TextBlock HEIGHT="" WIDTH="" HPOS="" VPOS="">
20
+ <TextLine HEIGHT="" WIDTH="" HPOS="" VPOS="">
21
+ <String HEIGHT="" WIDTH="" HPOS="" VPOS="" CONTENT="This"></String>
22
+ <String HEIGHT="" WIDTH="" HPOS="" VPOS="" CONTENT="is"></String>
23
+ <String HEIGHT="" WIDTH="" HPOS="" VPOS="" CONTENT="only"></String>
24
+ <String HEIGHT="" WIDTH="" HPOS="" VPOS="" CONTENT="a"></String>
25
+ <String HEIGHT="" WIDTH="" HPOS="" VPOS="" CONTENT="test."></String>
26
+ </TextLine>
27
+ </TextBlock>
28
+ </PrintSpace>
29
+ </Page>
30
+ </Layout>
31
+ </alto>