iiif_print 1.0.0 → 2.0.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (181) hide show
  1. checksums.yaml +4 -4
  2. data/.github/ISSUE_TEMPLATE.md +18 -0
  3. data/.github/PULL_REQUEST_TEMPLATE.md +16 -0
  4. data/.github/workflows/build-lint-test-action.yaml +4 -5
  5. data/.gitignore +5 -4
  6. data/.rubocop.yml +1 -0
  7. data/.solargraph.yml +19 -0
  8. data/Gemfile.lock +1025 -0
  9. data/README.md +102 -9
  10. data/Rakefile +6 -0
  11. data/app/actors/iiif_print/actors/cleanup_file_sets_actor_decorator.rb +24 -0
  12. data/app/actors/iiif_print/actors/file_set_actor_decorator.rb +30 -28
  13. data/app/controllers/iiif_print/split_pdfs_controller.rb +38 -0
  14. data/app/helpers/iiif_print/iiif_helper_decorator.rb +32 -0
  15. data/app/helpers/iiif_print/iiif_print_helper_behavior.rb +23 -0
  16. data/app/helpers/iiif_print_helper.rb +0 -20
  17. data/app/indexers/concerns/iiif_print/child_work_indexer.rb +27 -0
  18. data/app/indexers/concerns/iiif_print/file_set_indexer.rb +45 -17
  19. data/{lib → app/jobs}/iiif_print/jobs/application_job.rb +2 -1
  20. data/app/jobs/iiif_print/jobs/child_works_from_pdf_job.rb +153 -0
  21. data/app/jobs/iiif_print/jobs/create_relationships_job.rb +117 -0
  22. data/app/jobs/iiif_print/jobs/request_split_pdf_job.rb +31 -0
  23. data/app/listeners/iiif_print/listener.rb +31 -0
  24. data/app/models/concerns/iiif_print/set_child_flag.rb +10 -1
  25. data/app/models/concerns/iiif_print/solr/document.rb +19 -3
  26. data/app/models/iiif_print/iiif_search_decorator.rb +35 -0
  27. data/app/models/iiif_print/iiif_search_response_decorator.rb +25 -2
  28. data/app/models/iiif_print/pending_relationship.rb +3 -0
  29. data/app/presenters/iiif_print/file_set_presenter_decorator.rb +11 -0
  30. data/app/presenters/iiif_print/iiif_manifest_presenter_behavior.rb +120 -0
  31. data/app/presenters/iiif_print/iiif_manifest_presenter_factory_behavior.rb +1 -1
  32. data/app/presenters/iiif_print/work_show_presenter_decorator.rb +23 -11
  33. data/app/search_builders/concerns/iiif_print/allinson_flex_fields.rb +15 -0
  34. data/app/search_builders/concerns/iiif_print/highlight_search_params.rb +2 -1
  35. data/app/services/iiif_print/derivative_rodeo_service.rb +382 -0
  36. data/app/services/iiif_print/manifest_builder_service_behavior.rb +90 -31
  37. data/app/services/iiif_print/pluggable_derivative_service.rb +8 -10
  38. data/app/services/iiif_print/simple_schema_loader_decorator.rb +11 -0
  39. data/app/transactions/hyrax/transactions/iiif_print_container_decorator.rb +34 -0
  40. data/app/transactions/hyrax/transactions/steps/conditionally_destroy_children_from_split.rb +32 -0
  41. data/app/transactions/hyrax/transactions/steps/delete_all_file_sets_decorator.rb +35 -0
  42. data/app/views/catalog/_index_header_list_default.html.erb +13 -0
  43. data/app/views/hyrax/base/_representative_media.html.erb +4 -3
  44. data/app/views/hyrax/base/iiif_viewers/_universal_viewer.html.erb +1 -1
  45. data/app/views/hyrax/file_sets/_show_actions.html.erb +24 -0
  46. data/config/initializers/simple_schema_loader.rb +1 -0
  47. data/config/locales/iiif_print.en.yml +4 -0
  48. data/config/metadata/child_works_from_pdf_splitting.yaml +21 -0
  49. data/config/routes.rb +3 -0
  50. data/db/migrate/20181214181358_create_iiif_print_derivative_attachments.rb +8 -6
  51. data/db/migrate/20190107165909_create_iiif_print_ingest_file_relations.rb +7 -5
  52. data/db/migrate/20230109000000_create_iiif_print_pending_relationships.rb +8 -6
  53. data/db/migrate/20231110163052_add_model_details_to_iiif_print_pending_relationships.rb +7 -0
  54. data/docker-compose.yml +2 -2
  55. data/iiif_print.gemspec +11 -10
  56. data/lib/generators/iiif_print/install_generator.rb +21 -1
  57. data/lib/generators/iiif_print/templates/config/initializers/iiif_print.rb +11 -4
  58. data/lib/generators/iiif_print/templates/helpers/iiif_print_helper.rb +5 -0
  59. data/lib/iiif_print/base_derivative_service.rb +14 -2
  60. data/lib/iiif_print/blacklight_iiif_search/annotation_decorator.rb +58 -6
  61. data/lib/iiif_print/catalog_search_builder.rb +7 -3
  62. data/lib/iiif_print/configuration.rb +205 -8
  63. data/lib/iiif_print/data/fileset_helper.rb +3 -3
  64. data/lib/iiif_print/data/work_derivatives.rb +4 -4
  65. data/lib/iiif_print/engine.rb +53 -15
  66. data/lib/iiif_print/errors.rb +18 -0
  67. data/lib/iiif_print/homepage_search_builder.rb +17 -0
  68. data/lib/iiif_print/image_tool.rb +12 -8
  69. data/lib/iiif_print/jp2_derivative_service.rb +4 -1
  70. data/lib/iiif_print/lineage_service.rb +47 -13
  71. data/lib/iiif_print/metadata.rb +67 -48
  72. data/lib/iiif_print/pdf_derivative_service.rb +3 -1
  73. data/lib/iiif_print/persistence_layer/active_fedora_adapter.rb +189 -0
  74. data/lib/iiif_print/persistence_layer/valkyrie_adapter.rb +183 -0
  75. data/lib/iiif_print/persistence_layer.rb +118 -0
  76. data/lib/iiif_print/split_pdfs/base_splitter.rb +153 -0
  77. data/lib/iiif_print/split_pdfs/child_work_creation_from_pdf_service.rb +83 -37
  78. data/lib/iiif_print/split_pdfs/derivative_rodeo_splitter.rb +166 -0
  79. data/lib/iiif_print/split_pdfs/destroy_pdf_child_works_service.rb +22 -0
  80. data/lib/iiif_print/split_pdfs/pages_to_jpgs_splitter.rb +19 -0
  81. data/lib/iiif_print/split_pdfs/pages_to_pngs_splitter.rb +26 -0
  82. data/lib/iiif_print/split_pdfs/pages_to_tiffs_splitter.rb +41 -0
  83. data/lib/iiif_print/split_pdfs/pdf_image_extraction_service.rb +64 -59
  84. data/lib/iiif_print/text_extraction/hocr_reader.rb +7 -3
  85. data/lib/iiif_print/text_extraction/page_ocr.rb +5 -4
  86. data/lib/iiif_print/text_extraction_derivative_service.rb +4 -2
  87. data/lib/iiif_print/text_formats_from_alto_service.rb +3 -1
  88. data/lib/iiif_print/tiff_derivative_service.rb +3 -1
  89. data/lib/iiif_print/version.rb +1 -1
  90. data/lib/iiif_print.rb +210 -20
  91. data/lib/samvera/derivatives/configuration.rb +83 -0
  92. data/lib/samvera/derivatives/hyrax.rb +129 -0
  93. data/lib/samvera/derivatives.rb +238 -0
  94. data/tasks/copy_authorities_to_test_app.rake +11 -0
  95. data/tasks/iiif_print_dev.rake +4 -4
  96. metadata +111 -196
  97. data/app/helpers/hyrax/iiif_helper.rb +0 -22
  98. data/app/indexers/concerns/iiif_print/child_indexer.rb +0 -34
  99. data/app/views/hyrax/file_sets/_actions.html.erb +0 -45
  100. data/bin/rails +0 -13
  101. data/lib/iiif_print/jobs/child_works_from_pdf_job.rb +0 -107
  102. data/lib/iiif_print/jobs/create_relationships_job.rb +0 -78
  103. data/lib/iiif_print/split_pdfs/pages_into_images_service.rb +0 -130
  104. data/spec/.keep.txt +0 -1
  105. data/spec/factories/ability.rb +0 -6
  106. data/spec/factories/newspaper_issue.rb +0 -7
  107. data/spec/factories/newspaper_page.rb +0 -7
  108. data/spec/factories/newspaper_page_solr_document.rb +0 -12
  109. data/spec/factories/newspaper_title.rb +0 -8
  110. data/spec/factories/uploaded_pdf_file.rb +0 -9
  111. data/spec/factories/uploaded_txt_file.rb +0 -9
  112. data/spec/factories/user.rb +0 -13
  113. data/spec/fixtures/files/4.1.07.jp2 +0 -0
  114. data/spec/fixtures/files/4.1.07.tiff +0 -0
  115. data/spec/fixtures/files/README.md +0 -7
  116. data/spec/fixtures/files/alto-2-0.xsd +0 -714
  117. data/spec/fixtures/files/broken-truncated.pdf +0 -0
  118. data/spec/fixtures/files/credits.md +0 -16
  119. data/spec/fixtures/files/lowres-gray-via-ndnp-sample.tiff +0 -0
  120. data/spec/fixtures/files/minimal-1-page.pdf +0 -0
  121. data/spec/fixtures/files/minimal-2-page.pdf +0 -0
  122. data/spec/fixtures/files/minimal-alto.xml +0 -31
  123. data/spec/fixtures/files/ndnp-alto-sample.xml +0 -24
  124. data/spec/fixtures/files/ndnp-sample1-json.json +0 -1
  125. data/spec/fixtures/files/ndnp-sample1-txt.txt +0 -1
  126. data/spec/fixtures/files/ndnp-sample1.pdf +0 -0
  127. data/spec/fixtures/files/ocr_alto.xml +0 -202
  128. data/spec/fixtures/files/ocr_alto_scaled_4pts_per_px.xml +0 -202
  129. data/spec/fixtures/files/ocr_color.tiff +0 -0
  130. data/spec/fixtures/files/ocr_gray.jp2 +0 -0
  131. data/spec/fixtures/files/ocr_gray.tiff +0 -0
  132. data/spec/fixtures/files/ocr_mono.tiff +0 -0
  133. data/spec/fixtures/files/ocr_mono_text_hocr.html +0 -78
  134. data/spec/fixtures/files/page1.tiff +0 -0
  135. data/spec/fixtures/files/sample-4page-issue.pdf +0 -0
  136. data/spec/fixtures/files/sample-color-newsletter.pdf +0 -0
  137. data/spec/fixtures/files/thumbnail.jpg +0 -0
  138. data/spec/helpers/hyrax/iiif_helper_spec.rb +0 -65
  139. data/spec/helpers/iiif_print_helper_spec.rb +0 -43
  140. data/spec/iiif_print/base_derivative_service_spec.rb +0 -11
  141. data/spec/iiif_print/blacklight_iiif_search/annotation_decorator_spec.rb +0 -51
  142. data/spec/iiif_print/catalog_search_builder_spec.rb +0 -60
  143. data/spec/iiif_print/configuration_spec.rb +0 -67
  144. data/spec/iiif_print/data/work_derivatives_spec.rb +0 -245
  145. data/spec/iiif_print/data/work_file_spec.rb +0 -99
  146. data/spec/iiif_print/data/work_files_spec.rb +0 -237
  147. data/spec/iiif_print/image_tool_spec.rb +0 -109
  148. data/spec/iiif_print/jobs/child_works_from_pdf_job_spec.rb +0 -30
  149. data/spec/iiif_print/jobs/create_relationships_job_spec.rb +0 -17
  150. data/spec/iiif_print/jp2_image_metadata_spec.rb +0 -37
  151. data/spec/iiif_print/lineage_service_spec.rb +0 -13
  152. data/spec/iiif_print/metadata_spec.rb +0 -115
  153. data/spec/iiif_print/split_pdfs/pages_into_images_service_spec.rb +0 -6
  154. data/spec/iiif_print/text_extraction/alto_reader_spec.rb +0 -49
  155. data/spec/iiif_print/text_extraction/hocr_reader_spec.rb +0 -45
  156. data/spec/iiif_print/text_extraction/page_ocr_spec.rb +0 -84
  157. data/spec/iiif_print/text_extraction/render_alto_spec.rb +0 -54
  158. data/spec/iiif_print/text_extraction/word_coords_builder_spec.rb +0 -44
  159. data/spec/iiif_print_spec.rb +0 -51
  160. data/spec/misc_shared.rb +0 -111
  161. data/spec/models/iiif_print/derivative_attachment_spec.rb +0 -37
  162. data/spec/models/iiif_print/ingest_file_relation_spec.rb +0 -56
  163. data/spec/models/solr_document_spec.rb +0 -14
  164. data/spec/presenters/iiif_print/iiif_manifest_presenter_behavior_spec.rb +0 -19
  165. data/spec/presenters/iiif_print/iiif_manifest_presenter_factory_behavior_spec.rb +0 -49
  166. data/spec/services/iiif_print/jp2_derivative_service_spec.rb +0 -59
  167. data/spec/services/iiif_print/pdf_derivative_service_spec.rb +0 -66
  168. data/spec/services/iiif_print/pluggable_derivative_service_spec.rb +0 -178
  169. data/spec/services/iiif_print/text_extraction_derivative_service_spec.rb +0 -82
  170. data/spec/services/iiif_print/text_formats_from_alto_service_spec.rb +0 -127
  171. data/spec/services/iiif_print/tiff_derivative_service_spec.rb +0 -65
  172. data/spec/spec_helper.rb +0 -181
  173. data/spec/support/controller_level_helpers.rb +0 -28
  174. data/spec/support/iiif_print_models.rb +0 -127
  175. data/spec/test_app_templates/blacklight.yml +0 -9
  176. data/spec/test_app_templates/fedora.yml +0 -15
  177. data/spec/test_app_templates/lib/generators/test_app_generator.rb +0 -40
  178. data/spec/test_app_templates/redis.yml +0 -9
  179. data/spec/test_app_templates/solr/conf/schema.xml +0 -362
  180. data/spec/test_app_templates/solr/conf/solrconfig.xml +0 -322
  181. data/spec/test_app_templates/solr.yml +0 -7
data/spec/fixtures/files/credits.md DELETED
@@ -1,16 +0,0 @@
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-1-page.pdf DELETED
Binary file
data/spec/fixtures/files/minimal-2-page.pdf DELETED
Binary file
data/spec/fixtures/files/minimal-alto.xml DELETED
@@ -1,31 +0,0 @@
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>