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
@@ -0,0 +1,322 @@
1
+ <?xml version="1.0" encoding="UTF-8" ?>
2
+ <!--
3
+ Licensed to the Apache Software Foundation (ASF) under one or more
4
+ contributor license agreements. See the NOTICE file distributed with
5
+ this work for additional information regarding copyright ownership.
6
+ The ASF licenses this file to You under the Apache License, Version 2.0
7
+ (the "License"); you may not use this file except in compliance with
8
+ the License. You may obtain a copy of the License at
9
+
10
+ http://www.apache.org/licenses/LICENSE-2.0
11
+
12
+ Unless required by applicable law or agreed to in writing, software
13
+ distributed under the License is distributed on an "AS IS" BASIS,
14
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15
+ See the License for the specific language governing permissions and
16
+ limitations under the License.
17
+ -->
18
+
19
+ <!--
20
+ This is a stripped down config file used for a simple example...
21
+ It is *not* a good example to work from.
22
+ -->
23
+ <config>
24
+
25
+ <!-- Controls what version of Lucene various components of Solr
26
+ adhere to. Generally, you want to use the latest version to
27
+ get all bug fixes and improvements. It is highly recommended
28
+ that you fully re-index after changing this setting as it can
29
+ affect both how text is indexed and queried.
30
+ -->
31
+ <luceneMatchVersion>5.0.0</luceneMatchVersion>
32
+
33
+ <lib dir="${solr.install.dir:../../../..}/contrib/analysis-extras/lib" />
34
+ <lib dir="${solr.install.dir:../../../..}/contrib/analysis-extras/lucene-libs" />
35
+ <lib dir="${solr.install.dir:../../../..}/contrib/extraction/lib" regex=".*\.jar" />
36
+ <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-cell-\d.*\.jar" />
37
+
38
+ <directoryFactory name="DirectoryFactory"
39
+ class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}">
40
+ </directoryFactory>
41
+
42
+ <codecFactory class="solr.SchemaCodecFactory"/>
43
+
44
+ <schemaFactory class="ClassicIndexSchemaFactory"/>
45
+
46
+
47
+ <dataDir>${solr.blacklight-core.data.dir:}</dataDir>
48
+
49
+ <requestDispatcher handleSelect="true" >
50
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="2048000" />
51
+ </requestDispatcher>
52
+
53
+ <requestHandler name="/analysis/field" startup="lazy" class="solr.FieldAnalysisRequestHandler" />
54
+
55
+ <!-- config for the admin interface -->
56
+ <admin>
57
+ <defaultQuery>*:*</defaultQuery>
58
+ </admin>
59
+
60
+ <updateHandler class="solr.DirectUpdateHandler2">
61
+ <updateLog>
62
+ <str name="dir">${solr.ulog.dir:}</str>
63
+ </updateLog>
64
+
65
+ <autoCommit>
66
+ <maxTime>${solr.autoCommit.maxTime:15000}</maxTime>
67
+ <openSearcher>false</openSearcher>
68
+ </autoCommit>
69
+
70
+ <autoSoftCommit>
71
+ <maxTime>${solr.autoSoftCommit.maxTime:-1}</maxTime>
72
+ </autoSoftCommit>
73
+ </updateHandler>
74
+
75
+ <!-- SearchHandler
76
+
77
+ http://wiki.apache.org/solr/SearchHandler
78
+
79
+ For processing Search Queries, the primary Request Handler
80
+ provided with Solr is "SearchHandler" It delegates to a sequent
81
+ of SearchComponents (see below) and supports distributed
82
+ queries across multiple shards
83
+ -->
84
+ <requestHandler name="search" class="solr.SearchHandler" default="true">
85
+ <!-- default values for query parameters can be specified, these
86
+ will be overridden by parameters in the request
87
+ -->
88
+ <lst name="defaults">
89
+ <str name="defType">edismax</str>
90
+ <str name="echoParams">explicit</str>
91
+ <str name="q.alt">*:*</str>
92
+ <str name="mm">2&lt;-1 5&lt;-2 6&lt;90%</str>
93
+ <int name="qs">1</int>
94
+ <int name="ps">2</int>
95
+ <float name="tie">0.01</float>
96
+ <!-- this qf and pf are used by default, if not otherwise specified by
97
+ client. The default blacklight_config will use these for the
98
+ "keywords" search. See the author_qf/author_pf, title_qf, etc
99
+ below, which the default blacklight_config will specify for
100
+ those searches. You may also be interested in:
101
+ http://wiki.apache.org/solr/LocalParams
102
+ -->
103
+ <str name="qf">
104
+ id
105
+ title_tesim
106
+ author_tesim
107
+ subject_tesim
108
+ </str>
109
+ <str name="pf">
110
+ all_text_timv^10
111
+ </str>
112
+
113
+ <str name="author_qf">
114
+ author_tesim
115
+ </str>
116
+ <str name="author_pf">
117
+ </str>
118
+ <str name="title_qf">
119
+ title_tesim
120
+ </str>
121
+ <str name="title_pf">
122
+ </str>
123
+ <str name="subject_qf">
124
+ subject_tesim
125
+ </str>
126
+ <str name="subject_pf">
127
+ </str>
128
+
129
+ <str name="fl">
130
+ *,
131
+ score
132
+ </str>
133
+
134
+ <str name="facet">true</str>
135
+ <str name="facet.mincount">1</str>
136
+
137
+ <str name="spellcheck">true</str>
138
+ <str name="spellcheck.dictionary">default</str>
139
+ <str name="spellcheck.onlyMorePopular">true</str>
140
+ <str name="spellcheck.extendedResults">true</str>
141
+ <str name="spellcheck.collate">false</str>
142
+ <str name="spellcheck.count">5</str>
143
+
144
+ </lst>
145
+ <arr name="last-components">
146
+ <str>spellcheck</str>
147
+ </arr>
148
+ </requestHandler>
149
+
150
+ <requestHandler name="permissions" class="solr.SearchHandler" >
151
+ <lst name="defaults">
152
+ <str name="facet">off</str>
153
+ <str name="echoParams">all</str>
154
+ <str name="rows">1</str>
155
+ <str name="q">{!raw f=id v=$id}</str> <!-- use id=666 instead of q=id:666 -->
156
+ <str name="fl">
157
+ id,
158
+ access_ssim,
159
+ discover_access_group_ssim,discover_access_person_ssim,
160
+ read_access_group_ssim,read_access_person_ssim,
161
+ edit_access_group_ssim,edit_access_person_ssim,
162
+ depositor_ti,
163
+ embargo_release_date_dtsi
164
+ inheritable_access_ssim,
165
+ inheritable_discover_access_group_ssim,inheritable_discover_access_person_ssim,
166
+ inheritable_read_access_group_ssim,inheritable_read_access_person_ssim,
167
+ inheritable_edit_access_group_ssim,inheritable_edit_access_person_ssim,
168
+ inheritable_embargo_release_date_dtsi
169
+ </str>
170
+ </lst>
171
+ </requestHandler>
172
+
173
+ <requestHandler name="standard" class="solr.SearchHandler">
174
+ <lst name="defaults">
175
+ <str name="echoParams">explicit</str>
176
+ <str name="defType">lucene</str>
177
+ </lst>
178
+ </requestHandler>
179
+
180
+ <!-- for requests to get a single document; use id=666 instead of q=id:666 -->
181
+ <requestHandler name="document" class="solr.SearchHandler" >
182
+ <lst name="defaults">
183
+ <str name="echoParams">all</str>
184
+ <str name="fl">*</str>
185
+ <str name="rows">1</str>
186
+ <str name="q">{!term f=id v=$id}</str> <!-- use id=666 instead of q=id:666 -->
187
+ </lst>
188
+ </requestHandler>
189
+
190
+ <searchComponent name="termsComponent" class="solr.TermsComponent" />
191
+
192
+ <requestHandler name="/terms" class="solr.SearchHandler">
193
+ <lst name="defaults">
194
+ <bool name="terms">true</bool>
195
+ </lst>
196
+ <arr name="components">
197
+ <str>termsComponent</str>
198
+ </arr>
199
+ </requestHandler>
200
+
201
+ <!-- Spell Check
202
+
203
+ The spell check component can return a list of alternative spelling
204
+ suggestions.
205
+
206
+ http://wiki.apache.org/solr/SpellCheckComponent
207
+ -->
208
+ <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
209
+
210
+ <str name="queryAnalyzerFieldType">textSpell</str>
211
+
212
+ <!-- Multiple "Spell Checkers" can be declared and used by this
213
+ component
214
+ -->
215
+
216
+ <!-- a spellchecker built from a field of the main index, and
217
+ written to disk
218
+ -->
219
+ <lst name="spellchecker">
220
+ <str name="name">default</str>
221
+ <str name="field">spell</str>
222
+ <str name="spellcheckIndexDir">./spell</str>
223
+ <str name="buildOnOptimize">true</str>
224
+ </lst>
225
+ <lst name="spellchecker">
226
+ <str name="name">author</str>
227
+ <str name="field">author_spell</str>
228
+ <str name="spellcheckIndexDir">./spell_author</str>
229
+ <str name="accuracy">0.7</str>
230
+ <str name="buildOnOptimize">true</str>
231
+ </lst>
232
+ <lst name="spellchecker">
233
+ <str name="name">subject</str>
234
+ <str name="field">subject_spell</str>
235
+ <str name="spellcheckIndexDir">./spell_subject</str>
236
+ <str name="accuracy">0.7</str>
237
+ <str name="buildOnOptimize">true</str>
238
+ </lst>
239
+ <lst name="spellchecker">
240
+ <str name="name">title</str>
241
+ <str name="field">title_spell</str>
242
+ <str name="spellcheckIndexDir">./spell_title</str>
243
+ <str name="accuracy">0.7</str>
244
+ <str name="buildOnOptimize">true</str>
245
+ </lst>
246
+
247
+ <!-- a spellchecker that uses a different distance measure -->
248
+ <!--
249
+ <lst name="spellchecker">
250
+ <str name="name">jarowinkler</str>
251
+ <str name="field">spell</str>
252
+ <str name="distanceMeasure">
253
+ org.apache.lucene.search.spell.JaroWinklerDistance
254
+ </str>
255
+ <str name="spellcheckIndexDir">spellcheckerJaro</str>
256
+ </lst>
257
+ -->
258
+
259
+ <!-- a spellchecker that use an alternate comparator
260
+
261
+ comparatorClass be one of:
262
+ 1. score (default)
263
+ 2. freq (Frequency first, then score)
264
+ 3. A fully qualified class name
265
+ -->
266
+ <!--
267
+ <lst name="spellchecker">
268
+ <str name="name">freq</str>
269
+ <str name="field">lowerfilt</str>
270
+ <str name="spellcheckIndexDir">spellcheckerFreq</str>
271
+ <str name="comparatorClass">freq</str>
272
+ <str name="buildOnCommit">true</str>
273
+ -->
274
+
275
+ <!-- A spellchecker that reads the list of words from a file -->
276
+ <!--
277
+ <lst name="spellchecker">
278
+ <str name="classname">solr.FileBasedSpellChecker</str>
279
+ <str name="name">file</str>
280
+ <str name="sourceLocation">spellings.txt</str>
281
+ <str name="characterEncoding">UTF-8</str>
282
+ <str name="spellcheckIndexDir">spellcheckerFile</str>
283
+ </lst>
284
+ -->
285
+ </searchComponent>
286
+
287
+ <searchComponent name="suggest" class="solr.SuggestComponent">
288
+ <lst name="suggester">
289
+ <str name="name">mySuggester</str>
290
+ <str name="lookupImpl">FuzzyLookupFactory</str>
291
+ <str name="suggestAnalyzerFieldType">textSuggest</str>
292
+ <str name="buildOnCommit">true</str>
293
+ <str name="field">suggest</str>
294
+ </lst>
295
+ </searchComponent>
296
+
297
+ <requestHandler name="/suggest" class="solr.SearchHandler" startup="lazy">
298
+ <lst name="defaults">
299
+ <str name="suggest">true</str>
300
+ <str name="suggest.count">5</str>
301
+ <str name="suggest.dictionary">mySuggester</str>
302
+ </lst>
303
+ <arr name="components">
304
+ <str>suggest</str>
305
+ </arr>
306
+ </requestHandler>
307
+
308
+ <requestHandler name="/update/extract" class="org.apache.solr.handler.extraction.ExtractingRequestHandler">
309
+ <lst name="defaults">
310
+ <str name="fmap.Last-Modified">last_modified</str>
311
+ <str name="uprefix">ignored_</str>
312
+ </lst>
313
+ <!--Optional. Specify a path to a tika configuration file. See the Tika docs for details.-->
314
+ <!-- <str name="tika.config">/my/path/to/tika.config</str> -->
315
+ <!-- Optional. Specify one or more date formats to parse. See DateUtil.DEFAULT_DATE_FORMATS
316
+ for default date formats -->
317
+ <!-- <lst name="date.formats"> -->
318
+ <!-- <str>yyyy&#45;MM&#45;dd</str> -->
319
+ <!-- </lst> -->
320
+ </requestHandler>
321
+ </config>
322
+
@@ -0,0 +1,2 @@
1
+ pizza
2
+ history
@@ -0,0 +1,58 @@
1
+ # Licensed to the Apache Software Foundation (ASF) under one or more
2
+ # contributor license agreements. See the NOTICE file distributed with
3
+ # this work for additional information regarding copyright ownership.
4
+ # The ASF licenses this file to You under the Apache License, Version 2.0
5
+ # (the "License"); you may not use this file except in compliance with
6
+ # the License. You may obtain a copy of the License at
7
+ #
8
+ # http://www.apache.org/licenses/LICENSE-2.0
9
+ #
10
+ # Unless required by applicable law or agreed to in writing, software
11
+ # distributed under the License is distributed on an "AS IS" BASIS,
12
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13
+ # See the License for the specific language governing permissions and
14
+ # limitations under the License.
15
+
16
+ #-----------------------------------------------------------------------
17
+ # a couple of test stopwords to test that the words are really being
18
+ # configured from this file:
19
+ stopworda
20
+ stopwordb
21
+
22
+ #Standard english stop words taken from Lucene's StopAnalyzer
23
+ a
24
+ an
25
+ and
26
+ are
27
+ as
28
+ at
29
+ be
30
+ but
31
+ by
32
+ for
33
+ if
34
+ in
35
+ into
36
+ is
37
+ it
38
+ no
39
+ not
40
+ of
41
+ on
42
+ or
43
+ s
44
+ such
45
+ t
46
+ that
47
+ the
48
+ their
49
+ then
50
+ there
51
+ these
52
+ they
53
+ this
54
+ to
55
+ was
56
+ will
57
+ with
58
+
@@ -0,0 +1,58 @@
1
+ # Licensed to the Apache Software Foundation (ASF) under one or more
2
+ # contributor license agreements. See the NOTICE file distributed with
3
+ # this work for additional information regarding copyright ownership.
4
+ # The ASF licenses this file to You under the Apache License, Version 2.0
5
+ # (the "License"); you may not use this file except in compliance with
6
+ # the License. You may obtain a copy of the License at
7
+ #
8
+ # http://www.apache.org/licenses/LICENSE-2.0
9
+ #
10
+ # Unless required by applicable law or agreed to in writing, software
11
+ # distributed under the License is distributed on an "AS IS" BASIS,
12
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13
+ # See the License for the specific language governing permissions and
14
+ # limitations under the License.
15
+
16
+ #-----------------------------------------------------------------------
17
+ # a couple of test stopwords to test that the words are really being
18
+ # configured from this file:
19
+ stopworda
20
+ stopwordb
21
+
22
+ #Standard english stop words taken from Lucene's StopAnalyzer
23
+ a
24
+ an
25
+ and
26
+ are
27
+ as
28
+ at
29
+ be
30
+ but
31
+ by
32
+ for
33
+ if
34
+ in
35
+ into
36
+ is
37
+ it
38
+ no
39
+ not
40
+ of
41
+ on
42
+ or
43
+ s
44
+ such
45
+ t
46
+ that
47
+ the
48
+ their
49
+ then
50
+ there
51
+ these
52
+ they
53
+ this
54
+ to
55
+ was
56
+ will
57
+ with
58
+
@@ -0,0 +1,31 @@
1
+ # The ASF licenses this file to You under the Apache License, Version 2.0
2
+ # (the "License"); you may not use this file except in compliance with
3
+ # the License. You may obtain a copy of the License at
4
+ #
5
+ # http://www.apache.org/licenses/LICENSE-2.0
6
+ #
7
+ # Unless required by applicable law or agreed to in writing, software
8
+ # distributed under the License is distributed on an "AS IS" BASIS,
9
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
10
+ # See the License for the specific language governing permissions and
11
+ # limitations under the License.
12
+
13
+ #-----------------------------------------------------------------------
14
+ #some test synonym mappings unlikely to appear in real input text
15
+ aaa => aaaa
16
+ bbb => bbbb1 bbbb2
17
+ ccc => cccc1,cccc2
18
+ a\=>a => b\=>b
19
+ a\,a => b\,b
20
+ fooaaa,baraaa,bazaaa
21
+
22
+ # Some synonym groups specific to this example
23
+ GB,gib,gigabyte,gigabytes
24
+ MB,mib,megabyte,megabytes
25
+ Television, Televisions, TV, TVs
26
+ #notice we use "gib" instead of "GiB" so any WordDelimiterFilter coming
27
+ #after us won't split it into two words.
28
+
29
+ # Synonym mappings can be used for spelling correction too
30
+ pixima => pixma
31
+
@@ -0,0 +1,132 @@
1
+ <?xml version='1.0' encoding='UTF-8'?>
2
+
3
+ <!--
4
+ * Licensed to the Apache Software Foundation (ASF) under one or more
5
+ * contributor license agreements. See the NOTICE file distributed with
6
+ * this work for additional information regarding copyright ownership.
7
+ * The ASF licenses this file to You under the Apache License, Version 2.0
8
+ * (the "License"); you may not use this file except in compliance with
9
+ * the License. You may obtain a copy of the License at
10
+ *
11
+ * http://www.apache.org/licenses/LICENSE-2.0
12
+ *
13
+ * Unless required by applicable law or agreed to in writing, software
14
+ * distributed under the License is distributed on an "AS IS" BASIS,
15
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
16
+ * See the License for the specific language governing permissions and
17
+ * limitations under the License.
18
+ -->
19
+
20
+ <!--
21
+ Simple transform of Solr query results to HTML
22
+ -->
23
+ <xsl:stylesheet version='1.0'
24
+ xmlns:xsl='http://www.w3.org/1999/XSL/Transform'
25
+ >
26
+
27
+ <xsl:output media-type="text/html; charset=UTF-8" encoding="UTF-8"/>
28
+
29
+ <xsl:variable name="title" select="concat('Solr search results (',response/result/@numFound,' documents)')"/>
30
+
31
+ <xsl:template match='/'>
32
+ <html>
33
+ <head>
34
+ <title><xsl:value-of select="$title"/></title>
35
+ <xsl:call-template name="css"/>
36
+ </head>
37
+ <body>
38
+ <h1><xsl:value-of select="$title"/></h1>
39
+ <div class="note">
40
+ This has been formatted by the sample "example.xsl" transform -
41
+ use your own XSLT to get a nicer page
42
+ </div>
43
+ <xsl:apply-templates select="response/result/doc"/>
44
+ </body>
45
+ </html>
46
+ </xsl:template>
47
+
48
+ <xsl:template match="doc">
49
+ <xsl:variable name="pos" select="position()"/>
50
+ <div class="doc">
51
+ <table width="100%">
52
+ <xsl:apply-templates>
53
+ <xsl:with-param name="pos"><xsl:value-of select="$pos"/></xsl:with-param>
54
+ </xsl:apply-templates>
55
+ </table>
56
+ </div>
57
+ </xsl:template>
58
+
59
+ <xsl:template match="doc/*[@name='score']" priority="100">
60
+ <xsl:param name="pos"></xsl:param>
61
+ <tr>
62
+ <td class="name">
63
+ <xsl:value-of select="@name"/>
64
+ </td>
65
+ <td class="value">
66
+ <xsl:value-of select="."/>
67
+
68
+ <xsl:if test="boolean(//lst[@name='explain'])">
69
+ <xsl:element name="a">
70
+ <!-- can't allow whitespace here -->
71
+ <xsl:attribute name="href">javascript:toggle("<xsl:value-of select="concat('exp-',$pos)" />");</xsl:attribute>?</xsl:element>
72
+ <br/>
73
+ <xsl:element name="div">
74
+ <xsl:attribute name="class">exp</xsl:attribute>
75
+ <xsl:attribute name="id">
76
+ <xsl:value-of select="concat('exp-',$pos)" />
77
+ </xsl:attribute>
78
+ <xsl:value-of select="//lst[@name='explain']/str[position()=$pos]"/>
79
+ </xsl:element>
80
+ </xsl:if>
81
+ </td>
82
+ </tr>
83
+ </xsl:template>
84
+
85
+ <xsl:template match="doc/arr" priority="100">
86
+ <tr>
87
+ <td class="name">
88
+ <xsl:value-of select="@name"/>
89
+ </td>
90
+ <td class="value">
91
+ <ul>
92
+ <xsl:for-each select="*">
93
+ <li><xsl:value-of select="."/></li>
94
+ </xsl:for-each>
95
+ </ul>
96
+ </td>
97
+ </tr>
98
+ </xsl:template>
99
+
100
+
101
+ <xsl:template match="doc/*">
102
+ <tr>
103
+ <td class="name">
104
+ <xsl:value-of select="@name"/>
105
+ </td>
106
+ <td class="value">
107
+ <xsl:value-of select="."/>
108
+ </td>
109
+ </tr>
110
+ </xsl:template>
111
+
112
+ <xsl:template match="*"/>
113
+
114
+ <xsl:template name="css">
115
+ <script>
116
+ function toggle(id) {
117
+ var obj = document.getElementById(id);
118
+ obj.style.display = (obj.style.display != 'block') ? 'block' : 'none';
119
+ }
120
+ </script>
121
+ <style type="text/css">
122
+ body { font-family: "Lucida Grande", sans-serif }
123
+ td.name { font-style: italic; font-size:80%; }
124
+ td { vertical-align: top; }
125
+ ul { margin: 0px; margin-left: 1em; padding: 0px; }
126
+ .note { font-size:80%; }
127
+ .doc { margin-top: 1em; border-top: solid grey 1px; }
128
+ .exp { display: none; font-family: monospace; white-space: pre; }
129
+ </style>
130
+ </xsl:template>
131
+
132
+ </xsl:stylesheet>
@@ -0,0 +1,67 @@
1
+ <?xml version='1.0' encoding='UTF-8'?>
2
+
3
+ <!--
4
+ * Licensed to the Apache Software Foundation (ASF) under one or more
5
+ * contributor license agreements. See the NOTICE file distributed with
6
+ * this work for additional information regarding copyright ownership.
7
+ * The ASF licenses this file to You under the Apache License, Version 2.0
8
+ * (the "License"); you may not use this file except in compliance with
9
+ * the License. You may obtain a copy of the License at
10
+ *
11
+ * http://www.apache.org/licenses/LICENSE-2.0
12
+ *
13
+ * Unless required by applicable law or agreed to in writing, software
14
+ * distributed under the License is distributed on an "AS IS" BASIS,
15
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
16
+ * See the License for the specific language governing permissions and
17
+ * limitations under the License.
18
+ -->
19
+
20
+ <!--
21
+ Simple transform of Solr query results to Atom
22
+ -->
23
+
24
+ <xsl:stylesheet version='1.0'
25
+ xmlns:xsl='http://www.w3.org/1999/XSL/Transform'>
26
+
27
+ <xsl:output
28
+ method="xml"
29
+ encoding="utf-8"
30
+ media-type="text/xml; charset=UTF-8"
31
+ />
32
+
33
+ <xsl:template match='/'>
34
+ <xsl:variable name="query" select="response/lst[@name='responseHeader']/lst[@name='params']/str[@name='q']"/>
35
+ <feed xmlns="http://www.w3.org/2005/Atom">
36
+ <title>Example Solr Atom 1.0 Feed</title>
37
+ <subtitle>
38
+ This has been formatted by the sample "example_atom.xsl" transform -
39
+ use your own XSLT to get a nicer Atom feed.
40
+ </subtitle>
41
+ <author>
42
+ <name>Apache Solr</name>
43
+ <email>solr-user@lucene.apache.org</email>
44
+ </author>
45
+ <link rel="self" type="application/atom+xml"
46
+ href="http://localhost:8983/solr/q={$query}&amp;wt=xslt&amp;tr=atom.xsl"/>
47
+ <updated>
48
+ <xsl:value-of select="response/result/doc[position()=1]/date[@name='timestamp']"/>
49
+ </updated>
50
+ <id>tag:localhost,2007:example</id>
51
+ <xsl:apply-templates select="response/result/doc"/>
52
+ </feed>
53
+ </xsl:template>
54
+
55
+ <!-- search results xslt -->
56
+ <xsl:template match="doc">
57
+ <xsl:variable name="id" select="str[@name='id']"/>
58
+ <entry>
59
+ <title><xsl:value-of select="str[@name='name']"/></title>
60
+ <link href="http://localhost:8983/solr/select?q={$id}"/>
61
+ <id>tag:localhost,2007:<xsl:value-of select="$id"/></id>
62
+ <summary><xsl:value-of select="arr[@name='features']"/></summary>
63
+ <updated><xsl:value-of select="date[@name='timestamp']"/></updated>
64
+ </entry>
65
+ </xsl:template>
66
+
67
+ </xsl:stylesheet>