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/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/ocr_mono_text_hocr.html ADDED
@@ -0,0 +1,78 @@
1
+ <?xml version="1.0" encoding="UTF-8"?>
2
+ <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
3
+ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
4
+ <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
5
+ <head>
6
+ <title></title>
7
+ <meta http-equiv="Content-Type" content="text/html;charset=utf-8" />
8
+ <meta name='ocr-system' content='tesseract 4.0.0-beta.1' />
9
+ <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word'/>
10
+ </head>
11
+ <body>
12
+ <div class='ocr_page' id='page_1' title='image "ocr_mono.tiff"; bbox 0 0 1261 1744; ppageno 0'>
13
+ <div class='ocr_carea' id='block_1_1' title="bbox 155 22 1073 129">
14
+ <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 155 22 1073 129">
15
+ <span class='ocr_line' id='line_1_1' title="bbox 155 22 1073 129; baseline 0.003 -18; x_size 111; x_descenders 19; x_ascenders 40"><span class='ocrx_word' id='word_1_1' title='bbox 155 59 247 129; x_wconf 76'>_A</span> <span class='ocrx_word' id='word_1_2' title='bbox 272 28 600 113; x_wconf 95'>FEARFUL</span> <span class='ocrx_word' id='word_1_3' title='bbox 622 22 1073 129; x_wconf 85'>ADVENTURE.</span>
16
+ </span>
17
+ </p>
18
+ </div>
19
+ <div class='ocr_carea' id='block_1_2' title="bbox 551 152 695 161">
20
+ <p class='ocr_par' id='par_1_2' lang='eng' title="bbox 551 152 695 161">
21
+ <span class='ocr_line' id='line_1_2' title="bbox 551 152 695 161; baseline 0 0; x_size 4.5; x_descenders -2.25; x_ascenders 2.25"><span class='ocrx_word' id='word_1_4' title='bbox 551 152 695 161; x_wconf 95'> </span>
22
+ </span>
23
+ </p>
24
+ </div>
25
+ <div class='ocr_carea' id='block_1_3' title="bbox 11 174 1244 613">
26
+ <p class='ocr_par' id='par_1_3' lang='eng' title="bbox 11 174 1242 429">
27
+ <span class='ocr_line' id='line_1_3' title="bbox 69 174 1242 261; baseline 0.003 -21; x_size 70; x_descenders 18; x_ascenders 18"><span class='ocrx_word' id='word_1_5' title='bbox 69 188 193 240; x_wconf 57'>‘The</span> <span class='ocrx_word' id='word_1_6' title='bbox 225 191 464 244; x_wconf 52'>Missouri.</span> <span class='ocrx_word' id='word_1_7' title='bbox 517 174 865 261; x_wconf 92'>Republican,</span> <span class='ocrx_word' id='word_1_8' title='bbox 906 195 954 246; x_wconf 95'>in</span> <span class='ocrx_word' id='word_1_9' title='bbox 1007 211 1040 247; x_wconf 77'>a</span> <span class='ocrx_word' id='word_1_10' title='bbox 1087 195 1242 246; x_wconf 90'>letter</span>
28
+ </span>
29
+ <span class='ocr_line' id='line_1_4' title="bbox 11 270 1238 387; baseline 0.006 -63; x_size 71; x_descenders 18; x_ascenders 18"><span class='ocrx_word' id='word_1_11' title='bbox 11 270 139 326; x_wconf 96'>from</span> <span class='ocrx_word' id='word_1_12' title='bbox 167 293 199 328; x_wconf 93'>a</span> <span class='ocrx_word' id='word_1_13' title='bbox 229 277 440 329; x_wconf 95'>Kansas</span> <span class='ocrx_word' id='word_1_14' title='bbox 464 281 888 374; x_wconf 94'>correspondent,</span> <span class='ocrx_word' id='word_1_15' title='bbox 903 281 1008 387; x_wconf 96'>has</span> <span class='ocrx_word' id='word_1_16' title='bbox 1039 282 1128 333; x_wconf 93'>the</span> <span class='ocrx_word' id='word_1_17' title='bbox 1149 279 1238 332; x_wconf 92'>fol-</span>
30
+ </span>
31
+ <span class='ocr_line' id='line_1_5' title="bbox 12 361 224 429; baseline 0.021 -19; x_size 66; x_descenders 17; x_ascenders 16"><span class='ocrx_word' id='word_1_18' title='bbox 12 361 224 429; x_wconf 95'>lowing:</span>
32
+ </span>
33
+ </p>
34
+
35
+ <p class='ocr_par' id='par_1_4' lang='eng' title="bbox 11 407 1244 613">
36
+ <span class='ocr_line' id='line_1_6' title="bbox 86 407 1244 520; baseline 0.005 -19; x_size 70; x_descenders 16; x_ascenders 19"><span class='ocrx_word' id='word_1_19' title='bbox 86 452 206 501; x_wconf 95'>“At</span> <span class='ocrx_word' id='word_1_20' title='bbox 234 449 311 504; x_wconf 95'>St.</span> <span class='ocrx_word' id='word_1_21' title='bbox 339 415 567 520; x_wconf 49'>Josephs</span> <span class='ocrx_word' id='word_1_22' title='bbox 595 454 751 505; x_wconf 54'>Tsaw</span> <span class='ocrx_word' id='word_1_23' title='bbox 781 456 884 509; x_wconf 95'>Mr,</span> <span class='ocrx_word' id='word_1_24' title='bbox 915 457 982 508; x_wconf 91'>A.</span> <span class='ocrx_word' id='word_1_25' title='bbox 1011 456 1074 508; x_wconf 21'>&#39;T.</span> <span class='ocrx_word' id='word_1_26' title='bbox 1116 407 1244 508; x_wconf 91'>Gor-</span>
37
+ </span>
38
+ <span class='ocr_line' id='line_1_7' title="bbox 11 539 1242 613; baseline 0.006 -24; x_size 65; x_descenders 14; x_ascenders 16"><span class='ocrx_word' id='word_1_27' title='bbox 11 554 154 602; x_wconf 96'>man,</span> <span class='ocrx_word' id='word_1_28' title='bbox 177 539 228 590; x_wconf 95'>of</span> <span class='ocrx_word' id='word_1_29' title='bbox 260 539 389 592; x_wconf 95'>New</span> <span class='ocrx_word' id='word_1_30' title='bbox 417 542 580 606; x_wconf 96'>York,</span> <span class='ocrx_word' id='word_1_31' title='bbox 607 544 724 596; x_wconf 96'>who</span> <span class='ocrx_word' id='word_1_32' title='bbox 752 544 859 597; x_wconf 38'>had</span> <span class='ocrx_word' id='word_1_33' title='bbox 861 546 988 613; x_wconf 38'>just</span> <span class='ocrx_word' id='word_1_34' title='bbox 1012 562 1170 598; x_wconf 85'>come:</span> <span class='ocrx_word' id='word_1_35' title='bbox 1194 546 1242 597; x_wconf 96'>in</span>
39
+ </span>
40
+ </p>
41
+ </div>
42
+ <div class='ocr_carea' id='block_1_4' title="bbox 12 625 1261 699">
43
+ <p class='ocr_par' id='par_1_5' lang='eng' title="bbox 12 625 1261 699">
44
+ <span class='ocr_line' id='line_1_8' title="bbox 12 625 1261 699; baseline 0.007 -24; x_size 66; x_descenders 16; x_ascenders 15"><span class='ocrx_word' id='word_1_36' title='bbox 12 625 140 676; x_wconf 95'>from</span> <span class='ocrx_word' id='word_1_37' title='bbox 163 627 257 679; x_wconf 96'>the</span> <span class='ocrx_word' id='word_1_38' title='bbox 287 631 576 680; x_wconf 95'>mountains</span> <span class='ocrx_word' id='word_1_39' title='bbox 599 631 650 682; x_wconf 94'>in</span> <span class='ocrx_word' id='word_1_40' title='bbox 678 632 802 683; x_wconf 89'>such</span> <span class='ocrx_word' id='word_1_41' title='bbox 824 648 855 682; x_wconf 89'>a</span> <span class='ocrx_word' id='word_1_42' title='bbox 882 636 1019 683; x_wconf 85'>state</span> <span class='ocrx_word' id='word_1_43' title='bbox 1043 633 1097 683; x_wconf 92'>of</span> <span class='ocrx_word' id='word_1_44' title='bbox 1109 637 1261 699; x_wconf 88'>pros-</span>
45
+ </span>
46
+ </p>
47
+ </div>
48
+ <div class='ocr_carea' id='block_1_5' title="bbox 11 714 1249 1742">
49
+ <p class='ocr_par' id='par_1_6' lang='eng' title="bbox 11 714 1249 1742">
50
+ <span class='ocr_line' id='line_1_9' title="bbox 12 714 1244 787; baseline 0.006 -23; x_size 69; x_descenders 17; x_ascenders 17"><span class='ocrx_word' id='word_1_45' title='bbox 12 714 209 765; x_wconf 95'>tration</span> <span class='ocrx_word' id='word_1_46' title='bbox 238 717 339 783; x_wconf 93'>and</span> <span class='ocrx_word' id='word_1_47' title='bbox 372 717 611 769; x_wconf 91'>affiiction</span> <span class='ocrx_word' id='word_1_48' title='bbox 645 734 701 769; x_wconf 96'>as</span> <span class='ocrx_word' id='word_1_49' title='bbox 746 719 896 772; x_wconf 95'>could</span> <span class='ocrx_word' id='word_1_50' title='bbox 950 722 1067 787; x_wconf 96'>only</span> <span class='ocrx_word' id='word_1_51' title='bbox 1112 719 1244 772; x_wconf 96'>have</span>
51
+ </span>
52
+ <span class='ocr_line' id='line_1_10' title="bbox 15 803 1245 882; baseline 0.005 -29; x_size 70; x_descenders 19; x_ascenders 16"><span class='ocrx_word' id='word_1_52' title='bbox 15 803 139 854; x_wconf 95'>been</span> <span class='ocrx_word' id='word_1_53' title='bbox 168 805 474 858; x_wconf 91'>occasioned</span> <span class='ocrx_word' id='word_1_54' title='bbox 514 808 582 873; x_wconf 95'>by</span> <span class='ocrx_word' id='word_1_55' title='bbox 608 807 748 859; x_wconf 96'>such</span> <span class='ocrx_word' id='word_1_56' title='bbox 795 824 1065 882; x_wconf 86'>exposure,</span> <span class='ocrx_word' id='word_1_57' title='bbox 1074 808 1245 859; x_wconf 86'>hard-</span>
53
+ </span>
54
+ <span class='ocr_line' id='line_1_11' title="bbox 11 892 1244 966; baseline 0.006 -26; x_size 71; x_descenders 20; x_ascenders 16"><span class='ocrx_word' id='word_1_58' title='bbox 11 892 125 960; x_wconf 95'>ship</span> <span class='ocrx_word' id='word_1_59' title='bbox 155 896 256 944; x_wconf 96'>and</span> <span class='ocrx_word' id='word_1_60' title='bbox 296 894 561 963; x_wconf 91'>suffering,</span> <span class='ocrx_word' id='word_1_61' title='bbox 590 913 649 947; x_wconf 91'>as</span> <span class='ocrx_word' id='word_1_62' title='bbox 699 898 925 966; x_wconf 94'>perhaps</span> <span class='ocrx_word' id='word_1_63' title='bbox 974 913 1042 949; x_wconf 91'>no</span> <span class='ocrx_word' id='word_1_64' title='bbox 1090 898 1244 948; x_wconf 91'>other</span>
55
+ </span>
56
+ <span class='ocr_line' id='line_1_12' title="bbox 14 983 1245 1053; baseline 0.005 -23; x_size 71; x_descenders 19; x_ascenders 18"><span class='ocrx_word' id='word_1_65' title='bbox 14 995 128 1030; x_wconf 96'>man</span> <span class='ocrx_word' id='word_1_66' title='bbox 156 997 279 1031; x_wconf 92'>ever</span> <span class='ocrx_word' id='word_1_67' title='bbox 306 983 560 1034; x_wconf 88'>snrvived.</span> <span class='ocrx_word' id='word_1_68' title='bbox 635 984 703 1034; x_wconf 47'>din</span> <span class='ocrx_word' id='word_1_69' title='bbox 732 999 985 1053; x_wconf 47'>company</span> <span class='ocrx_word' id='word_1_70' title='bbox 1042 984 1161 1049; x_wconf 96'>with</span> <span class='ocrx_word' id='word_1_71' title='bbox 1214 1002 1245 1036; x_wconf 93'>a</span>
57
+ </span>
58
+ <span class='ocr_line' id='line_1_13' title="bbox 15 1065 1246 1126; baseline 0.004 -11; x_size 62; x_descenders 10; x_ascenders 18"><span class='ocrx_word' id='word_1_72' title='bbox 15 1065 283 1126; x_wconf 47'>Canadian</span> <span class='ocrx_word' id='word_1_73' title='bbox 312 1066 638 1120; x_wconf 96'>Frenchman</span> <span class='ocrx_word' id='word_1_74' title='bbox 669 1071 774 1122; x_wconf 94'>and</span> <span class='ocrx_word' id='word_1_75' title='bbox 804 1077 908 1122; x_wconf 91'>two</span> <span class='ocrx_word' id='word_1_76' title='bbox 961 1069 1246 1123; x_wconf 91'>Kentucki-</span>
59
+ </span>
60
+ <span class='ocr_line' id='line_1_14' title="bbox 12 1153 1248 1223; baseline 0.006 -22; x_size 68; x_descenders 17; x_ascenders 18"><span class='ocrx_word' id='word_1_77' title='bbox 12 1169 105 1202; x_wconf 90'>ans</span> <span class='ocrx_word' id='word_1_78' title='bbox 132 1153 310 1205; x_wconf 85'>he-left</span> <span class='ocrx_word' id='word_1_79' title='bbox 337 1155 425 1205; x_wconf 96'>the</span> <span class='ocrx_word' id='word_1_80' title='bbox 452 1162 672 1223; x_wconf 96'>country</span> <span class='ocrx_word' id='word_1_81' title='bbox 724 1157 783 1208; x_wconf 96'>of</span> <span class='ocrx_word' id='word_1_82' title='bbox 832 1157 927 1208; x_wconf 96'>the</span> <span class='ocrx_word' id='word_1_83' title='bbox 972 1157 1248 1209; x_wconf 90'>Blackfeet</span>
61
+ </span>
62
+ <span class='ocr_line' id='line_1_15' title="bbox 16 1239 1246 1306; baseline 0.003 -18; x_size 69; x_descenders 15; x_ascenders 21"><span class='ocrx_word' id='word_1_84' title='bbox 16 1239 228 1311; x_wconf 88'>Indians</span> <span class='ocrx_word' id='word_1_85' title='bbox 247 1241 356 1310; x_wconf 64'>last</span> <span class='ocrx_word' id='word_1_86' title='bbox 366 1240 599 1288; x_wconf 36'>-Fall.:to</span> <span class='ocrx_word' id='word_1_87' title='bbox 623 1244 795 1315; x_wconf 86'>join.</span> <span class='ocrx_word' id='word_1_88' title='bbox 800 1243 1100 1310; x_wconf 76'>Culverson</span> <span class='ocrx_word' id='word_1_89' title='bbox 1140 1245 1246 1309; x_wconf 96'>and</span>
63
+ </span>
64
+ <span class='ocr_line' id='line_1_16' title="bbox 14 1303 1246 1393; baseline 0.003 -21; x_size 67; x_descenders 16; x_ascenders 16"><span class='ocrx_word' id='word_1_90' title='bbox 14 1309 167 1388; x_wconf 96'>party</span> <span class='ocrx_word' id='word_1_91' title='bbox 195 1307 253 1373; x_wconf 96'>at</span> <span class='ocrx_word' id='word_1_92' title='bbox 282 1305 413 1373; x_wconf 96'>Fort</span> <span class='ocrx_word' id='word_1_93' title='bbox 443 1313 623 1376; x_wconf 96'>Pierre</span> <span class='ocrx_word' id='word_1_94' title='bbox 647 1326 750 1376; x_wconf 93'>and</span> <span class='ocrx_word' id='word_1_95' title='bbox 774 1358 789 1375; x_wconf 91'>¢</span> <span class='ocrx_word' id='word_1_96' title='bbox 773 1313 1089 1393; x_wconf 96'>accompany</span> <span class='ocrx_word' id='word_1_97' title='bbox 1109 1303 1246 1376; x_wconf 96'>them</span>
65
+ </span>
66
+ <span class='ocr_line' id='line_1_17' title="bbox 15 1411 1245 1480; baseline 0.004 -19; x_size 68; x_descenders 17; x_ascenders 15"><span class='ocrx_word' id='word_1_98' title='bbox 15 1419 70 1462; x_wconf 96'>to</span> <span class='ocrx_word' id='word_1_99' title='bbox 99 1411 185 1462; x_wconf 96'>the</span> <span class='ocrx_word' id='word_1_100' title='bbox 213 1418 393 1463; x_wconf 96'>states.</span> <span class='ocrx_word' id='word_1_101' title='bbox 432 1412 579 1480; x_wconf 96'>They</span> <span class='ocrx_word' id='word_1_102' title='bbox 608 1414 816 1466; x_wconf 96'>arrived</span> <span class='ocrx_word' id='word_1_103' title='bbox 837 1420 894 1465; x_wconf 96'>at</span> <span class='ocrx_word' id='word_1_104' title='bbox 914 1414 1050 1465; x_wconf 96'>Fort</span> <span class='ocrx_word' id='word_1_105' title='bbox 1067 1414 1245 1466; x_wconf 96'>Pierre</span>
67
+ </span>
68
+ <span class='ocr_line' id='line_1_18' title="bbox 15 1497 1246 1568; baseline 0.002 -18; x_size 70; x_descenders 17; x_ascenders 18"><span class='ocrx_word' id='word_1_106' title='bbox 15 1505 120 1550; x_wconf 96'>two</span> <span class='ocrx_word' id='word_1_107' title='bbox 147 1500 276 1564; x_wconf 96'>days</span> <span class='ocrx_word' id='word_1_108' title='bbox 303 1497 436 1550; x_wconf 92'>after</span> <span class='ocrx_word' id='word_1_109' title='bbox 466 1497 794 1551; x_wconf 74'>Calverson’s</span> <span class='ocrx_word' id='word_1_110' title='bbox 821 1500 1116 1568; x_wconf 96'>departure,</span> <span class='ocrx_word' id='word_1_111' title='bbox 1145 1502 1246 1552; x_wconf 96'>and</span>
69
+ </span>
70
+ <span class='ocr_line' id='line_1_19' title="bbox 15 1586 1249 1656; baseline 0.001 -19; x_size 68; x_descenders 17; x_ascenders 17"><span class='ocrx_word' id='word_1_112' title='bbox 15 1587 222 1638; x_wconf 51'>hurried</span> <span class='ocrx_word' id='word_1_113' title='bbox 252 1603 316 1638; x_wconf 96'>on</span> <span class='ocrx_word' id='word_1_114' title='bbox 343 1586 498 1650; x_wconf 96'>after,</span> <span class='ocrx_word' id='word_1_115' title='bbox 526 1587 578 1637; x_wconf 96'>in</span> <span class='ocrx_word' id='word_1_116' title='bbox 606 1587 693 1640; x_wconf 96'>the</span> <span class='ocrx_word' id='word_1_117' title='bbox 719 1587 853 1656; x_wconf 95'>hope</span> <span class='ocrx_word' id='word_1_118' title='bbox 874 1589 929 1640; x_wconf 95'>of</span> <span class='ocrx_word' id='word_1_119' title='bbox 939 1589 1249 1656; x_wconf 96'>overtaking</span>
71
+ </span>
72
+ <span class='ocr_line' id='line_1_20' title="bbox 18 1672 1248 1742; baseline 0.001 -16; x_size 69; x_descenders 16; x_ascenders 18"><span class='ocrx_word' id='word_1_120' title='bbox 18 1675 160 1734; x_wconf 90'>him.</span> <span class='ocrx_word' id='word_1_121' title='bbox 214 1672 296 1726; x_wconf 92'>On</span> <span class='ocrx_word' id='word_1_122' title='bbox 327 1675 416 1726; x_wconf 95'>the</span> <span class='ocrx_word' id='word_1_123' title='bbox 442 1675 584 1727; x_wconf 96'>third</span> <span class='ocrx_word' id='word_1_124' title='bbox 608 1675 711 1742; x_wconf 96'>day</span> <span class='ocrx_word' id='word_1_125' title='bbox 740 1691 837 1727; x_wconf 96'>one</span> <span class='ocrx_word' id='word_1_126' title='bbox 865 1676 922 1727; x_wconf 96'>of</span> <span class='ocrx_word' id='word_1_127' title='bbox 942 1675 1090 1727; x_wconf 96'>those</span> <span class='ocrx_word' id='word_1_128' title='bbox 1110 1692 1248 1727; x_wconf 96'>snow</span>
73
+ </span>
74
+ </p>
75
+ </div>
76
+ </div>
77
+ </body>
78
+ </html>
data/spec/fixtures/files/page1.tiff ADDED
Binary file
data/spec/fixtures/files/thumbnail.jpg ADDED
Binary file