mabmapper 1.0.0.pre15

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (221) hide show
  1. checksums.yaml +7 -0
  2. data/.gitignore +20 -0
  3. data/.travis.yml +4 -0
  4. data/Gemfile +7 -0
  5. data/LICENSE +22 -0
  6. data/README.md +49 -0
  7. data/Rakefile +29 -0
  8. data/bin/mabmapper +3 -0
  9. data/lib/mabmapper/aleph_mab_xml_engine.rb +1050 -0
  10. data/lib/mabmapper/cli.rb +216 -0
  11. data/lib/mabmapper/elasticsearch_writer.rb +52 -0
  12. data/lib/mabmapper/engine.rb +112 -0
  13. data/lib/mabmapper/mab_xml/document.rb +53 -0
  14. data/lib/mabmapper/mab_xml/field.rb +43 -0
  15. data/lib/mabmapper/mab_xml/query.rb +25 -0
  16. data/lib/mabmapper/mab_xml/query_helper.rb +101 -0
  17. data/lib/mabmapper/mab_xml/result_set.rb +34 -0
  18. data/lib/mabmapper/mab_xml/subfield.rb +12 -0
  19. data/lib/mabmapper/mab_xml.rb +6 -0
  20. data/lib/mabmapper/tar_writer.rb +29 -0
  21. data/lib/mabmapper/version.rb +3 -0
  22. data/lib/mabmapper.rb +11 -0
  23. data/mabmapper.gemspec +33 -0
  24. data/test/mab_files/test_creation_date/test1.xml +17 -0
  25. data/test/mab_files/test_creation_date/test2.xml +17 -0
  26. data/test/mab_files/test_creationdate/425_a_1.xml +17 -0
  27. data/test/mab_files/test_creationdate/425_a_2.xml +19 -0
  28. data/test/mab_files/test_creationdate/425_bc_1.xml +19 -0
  29. data/test/mab_files/test_creationdate/425_bc_2.xml +22 -0
  30. data/test/mab_files/test_creationdate/425_bc_3.xml +22 -0
  31. data/test/mab_files/test_creationdate/425_bc_4.xml +19 -0
  32. data/test/mab_files/test_creationdate/425_p_1.xml +19 -0
  33. data/test/mab_files/test_creationdate/425_p_2.xml +17 -0
  34. data/test/mab_files/test_creationdate/595_1.xml +20 -0
  35. data/test/mab_files/test_creator_contributor_facet/PAD01.001006945.PRIMO.xml +574 -0
  36. data/test/mab_files/test_description/405.xml +22 -0
  37. data/test/mab_files/test_description/501-519.xml +30 -0
  38. data/test/mab_files/test_description/522.xml +22 -0
  39. data/test/mab_files/test_description/523.xml +22 -0
  40. data/test/mab_files/test_description/536-537.xml +30 -0
  41. data/test/mab_files/test_doc/PAD01.001510737.PRIMO.xml +317 -0
  42. data/test/mab_files/test_edition/PAD01.000844686.PRIMO.xml +584 -0
  43. data/test/mab_files/test_edition/PAD01.000969531.PRIMO.xml +129 -0
  44. data/test/mab_files/test_edition/PAD01.000969710.PRIMO.xml +144 -0
  45. data/test/mab_files/test_edition/PAD01.000978033.PRIMO.xml +163 -0
  46. data/test/mab_files/test_edition/PAD01.000990520.PRIMO.xml +163 -0
  47. data/test/mab_files/test_erscheinungsform/PAD01.000870753.PRIMO.xml +256 -0
  48. data/test/mab_files/test_erscheinungsform/PAD01.000870755.PRIMO.xml +467 -0
  49. data/test/mab_files/test_ht_number/PAD01.001015067.PRIMO.xml +137 -0
  50. data/test/mab_files/test_inhaltstyp/PAD01.000870753.PRIMO.xml +256 -0
  51. data/test/mab_files/test_inhaltstyp/PAD01.000870755.PRIMO.xml +467 -0
  52. data/test/mab_files/test_is_secondary_form/PAD01.000806191.PRIMO.xml +216 -0
  53. data/test/mab_files/test_is_secondary_form/PAD01.000844686.PRIMO.xml +584 -0
  54. data/test/mab_files/test_is_secondary_form/PAD01.001015067.PRIMO.xml +137 -0
  55. data/test/mab_files/test_is_secondary_form/PAD01.001452439.PRIMO.xml +377 -0
  56. data/test/mab_files/test_is_suborder/PAD01.000806191.PRIMO.xml +216 -0
  57. data/test/mab_files/test_is_suborder/PAD01.000844686.PRIMO.xml +584 -0
  58. data/test/mab_files/test_is_suborder/PAD01.001452439.PRIMO.xml +377 -0
  59. data/test/mab_files/test_issn/PAD01.000637121.PRIMO.xml +805 -0
  60. data/test/mab_files/test_materialtyp/PAD01.000870753.PRIMO.xml +256 -0
  61. data/test/mab_files/test_materialtyp/PAD01.000870755.PRIMO.xml +467 -0
  62. data/test/mab_files/test_notation_sort/PAD01.000970649.PRIMO.xml +306 -0
  63. data/test/mab_files/test_notation_sort/PAD01.001006944.PRIMO.xml +279 -0
  64. data/test/mab_files/test_publisher/PAD01.000312406.PRIMO.xml +1043 -0
  65. data/test/mab_files/test_redactional_remark/PAD01.001510737.PRIMO.xml +317 -0
  66. data/test/mab_files/test_relation/PAD01.000438377.PRIMO.xml +232 -0
  67. data/test/mab_files/test_relation/PAD01.000637121.PRIMO.xml +810 -0
  68. data/test/mab_files/test_relation/PAD01.000806191.PRIMO.xml +216 -0
  69. data/test/mab_files/test_relation/PAD01.000844686.PRIMO.xml +584 -0
  70. data/test/mab_files/test_relation/PAD01.001452439.PRIMO.xml +377 -0
  71. data/test/mab_files/test_secondary_form_creationdate/PAD01.000806191.PRIMO.xml +216 -0
  72. data/test/mab_files/test_secondary_form_creationdate/PAD01.000844686.PRIMO.xml +584 -0
  73. data/test/mab_files/test_secondary_form_creationdate/PAD01.001452439.PRIMO.xml +377 -0
  74. data/test/mab_files/test_secondary_form_isbn/PAD01.000806191.PRIMO.xml +216 -0
  75. data/test/mab_files/test_secondary_form_isbn/PAD01.000844686.PRIMO.xml +584 -0
  76. data/test/mab_files/test_secondary_form_isbn/PAD01.001452439.PRIMO.xml +377 -0
  77. data/test/mab_files/test_secondary_form_physical_description/PAD01.000806191.PRIMO.xml +216 -0
  78. data/test/mab_files/test_secondary_form_physical_description/PAD01.001452439.PRIMO.xml +377 -0
  79. data/test/mab_files/test_secondary_form_preliminary_phrase/PAD01.000806191.PRIMO.xml +216 -0
  80. data/test/mab_files/test_secondary_form_preliminary_phrase/PAD01.001452439.PRIMO.xml +377 -0
  81. data/test/mab_files/test_secondary_form_publisher/PAD01.000806191.PRIMO.xml +216 -0
  82. data/test/mab_files/test_secondary_form_publisher/PAD01.001452439.PRIMO.xml +377 -0
  83. data/test/mab_files/test_secondary_form_superorder/PAD01.000806191.PRIMO.xml +216 -0
  84. data/test/mab_files/test_secondary_form_superorder/PAD01.000977734.PRIMO.xml +225 -0
  85. data/test/mab_files/test_secondary_form_superorder/PAD01.001452439.PRIMO.xml +377 -0
  86. data/test/mab_files/test_short_title_display/PAD01.000057960.PRIMO.xml +1069 -0
  87. data/test/mab_files/test_short_title_display/PAD01.000058000.PRIMO.xml +995 -0
  88. data/test/mab_files/test_short_title_display/PAD01.000215104.PRIMO.xml +191 -0
  89. data/test/mab_files/test_short_title_display/PAD01.000310864.PRIMO.xml +999 -0
  90. data/test/mab_files/test_short_title_display/PAD01.000392641.PRIMO.xml +4334 -0
  91. data/test/mab_files/test_short_title_display/PAD01.000392645.PRIMO.xml +4094 -0
  92. data/test/mab_files/test_short_title_display/PAD01.000438377.PRIMO.xml +232 -0
  93. data/test/mab_files/test_short_title_display/PAD01.000479391.PRIMO.xml +142 -0
  94. data/test/mab_files/test_short_title_display/PAD01.000637121.PRIMO.xml +805 -0
  95. data/test/mab_files/test_short_title_display/PAD01.000676616.PRIMO.xml +128 -0
  96. data/test/mab_files/test_short_title_display/PAD01.000782994.PRIMO.xml +169 -0
  97. data/test/mab_files/test_short_title_display/PAD01.001006945.PRIMO.xml +574 -0
  98. data/test/mab_files/test_short_title_display/PAD01.001015067.PRIMO.xml +137 -0
  99. data/test/mab_files/test_short_title_display/PAD01.001015070.PRIMO.xml +212 -0
  100. data/test/mab_files/test_short_title_display/PAD01.001108212.PRIMO.xml +259 -0
  101. data/test/mab_files/test_short_title_display/PAD01.001249043.PRIMO.xml +172 -0
  102. data/test/mab_files/test_short_title_display/PAD01.001499877.PRIMO.xml +227 -0
  103. data/test/mab_files/test_short_title_display/PAD01.001499879.PRIMO.xml +255 -0
  104. data/test/mab_files/test_short_title_display/PAD01.001499880.PRIMO.xml +279 -0
  105. data/test/mab_files/test_short_title_display/PAD01.001510878.PRIMO.xml +184 -0
  106. data/test/mab_files/test_short_title_display/PAD01.001562173.PRIMO.xml +116 -0
  107. data/test/mab_files/test_short_title_display/PAD01.001568334.PRIMO.xml +1840 -0
  108. data/test/mab_files/test_short_title_display/PAD01.001572048.PRIMO.xml +68 -0
  109. data/test/mab_files/test_short_title_display/PAD01.001572049.PRIMO.xml +133 -0
  110. data/test/mab_files/test_signature/PAD01.000161445.PRIMO.xml +149 -0
  111. data/test/mab_files/test_signature/PAD01.000321365.PRIMO.xml +343 -0
  112. data/test/mab_files/test_signature/PAD01.000636652.PRIMO.xml +217 -0
  113. data/test/mab_files/test_signature/PAD01.000857994.PRIMO.xml +187 -0
  114. data/test/mab_files/test_signature/PAD01.000859176.PRIMO.xml +559 -0
  115. data/test/mab_files/test_signature/PAD01.000969442.PRIMO.xml +210 -0
  116. data/test/mab_files/test_signature/PAD01.001006945.PRIMO.xml +574 -0
  117. data/test/mab_files/test_signature_search/PAD01.000161445.PRIMO.xml +149 -0
  118. data/test/mab_files/test_signature_search/PAD01.000321365.PRIMO.xml +343 -0
  119. data/test/mab_files/test_signature_search/PAD01.000636652.PRIMO.xml +217 -0
  120. data/test/mab_files/test_signature_search/PAD01.000857994.PRIMO.xml +187 -0
  121. data/test/mab_files/test_signature_search/PAD01.000859176.PRIMO.xml +559 -0
  122. data/test/mab_files/test_signature_search/PAD01.000969442.PRIMO.xml +210 -0
  123. data/test/mab_files/test_signature_search/PAD01.001006945.PRIMO.xml +574 -0
  124. data/test/mab_files/test_status/PAD01.000321365.PRIMO.xml +343 -0
  125. data/test/mab_files/test_status/PAD01.000392641.PRIMO.xml +4337 -0
  126. data/test/mab_files/test_status/detmold_1.xml +17 -0
  127. data/test/mab_files/test_status/detmold_2.xml +17 -0
  128. data/test/mab_files/test_status/detmold_3.xml +12 -0
  129. data/test/mab_files/test_subject/PAD01.000972511.PRIMO.xml +406 -0
  130. data/test/mab_files/test_suborders/PAD01.000057960.PRIMO.xml +1069 -0
  131. data/test/mab_files/test_suborders/PAD01.000058000.PRIMO.xml +995 -0
  132. data/test/mab_files/test_suborders/PAD01.000215104.PRIMO.xml +191 -0
  133. data/test/mab_files/test_suborders/PAD01.000310864.PRIMO.xml +999 -0
  134. data/test/mab_files/test_suborders/PAD01.000392641.PRIMO.xml +4334 -0
  135. data/test/mab_files/test_suborders/PAD01.000392645.PRIMO.xml +4094 -0
  136. data/test/mab_files/test_suborders/PAD01.000438377.PRIMO.xml +232 -0
  137. data/test/mab_files/test_suborders/PAD01.000479391.PRIMO.xml +142 -0
  138. data/test/mab_files/test_suborders/PAD01.000637121.PRIMO.xml +805 -0
  139. data/test/mab_files/test_suborders/PAD01.000676616.PRIMO.xml +128 -0
  140. data/test/mab_files/test_suborders/PAD01.001006945.PRIMO.xml +574 -0
  141. data/test/mab_files/test_suborders/PAD01.001015067.PRIMO.xml +137 -0
  142. data/test/mab_files/test_suborders/PAD01.001015068.PRIMO.xml +216 -0
  143. data/test/mab_files/test_suborders/PAD01.001015070.PRIMO.xml +212 -0
  144. data/test/mab_files/test_suborders/PAD01.001108212.PRIMO.xml +259 -0
  145. data/test/mab_files/test_suborders/PAD01.001499877.PRIMO.xml +227 -0
  146. data/test/mab_files/test_suborders/PAD01.001499879.PRIMO.xml +255 -0
  147. data/test/mab_files/test_suborders/PAD01.001499880.PRIMO.xml +279 -0
  148. data/test/mab_files/test_suborders/PAD01.001562173.PRIMO.xml +116 -0
  149. data/test/mab_files/test_suborders/PAD01.001572048.PRIMO.xml +68 -0
  150. data/test/mab_files/test_suborders/PAD01.001572049.PRIMO.xml +133 -0
  151. data/test/mab_files/test_superorder/PAD01.000806191.PRIMO.xml +216 -0
  152. data/test/mab_files/test_superorder/PAD01.000844686.PRIMO.xml +584 -0
  153. data/test/mab_files/test_superorder/PAD01.001015067.PRIMO.xml +137 -0
  154. data/test/mab_files/test_superorder/PAD01.001452439.PRIMO.xml +377 -0
  155. data/test/mab_files/test_superorder_display/PAD01.000000872.PRIMO.xml +227 -0
  156. data/test/mab_files/test_superorder_display/PAD01.000160412.PRIMO.xml +518 -0
  157. data/test/mab_files/test_superorder_display/PAD01.000162669.PRIMO.xml +198 -0
  158. data/test/mab_files/test_superorder_display/PAD01.000178500.PRIMO.xml +158 -0
  159. data/test/mab_files/test_superorder_display/PAD01.000297043.PRIMO.xml +154 -0
  160. data/test/mab_files/test_superorder_display/PAD01.000562878.PRIMO.xml +1214 -0
  161. data/test/mab_files/test_superorder_display/PAD01.000958473.PRIMO.xml +379 -0
  162. data/test/mab_files/test_superorder_display/PAD01.001006945.PRIMO.xml +574 -0
  163. data/test/mab_files/test_superorders/PAD01.000057960.PRIMO.xml +1069 -0
  164. data/test/mab_files/test_superorders/PAD01.000215104.PRIMO.xml +191 -0
  165. data/test/mab_files/test_superorders/PAD01.000310864.PRIMO.xml +999 -0
  166. data/test/mab_files/test_superorders/PAD01.000392641.PRIMO.xml +4334 -0
  167. data/test/mab_files/test_superorders/PAD01.000438377.PRIMO.xml +232 -0
  168. data/test/mab_files/test_superorders/PAD01.000479391.PRIMO.xml +142 -0
  169. data/test/mab_files/test_superorders/PAD01.000637121.PRIMO.xml +805 -0
  170. data/test/mab_files/test_superorders/PAD01.001015067.PRIMO.xml +137 -0
  171. data/test/mab_files/test_superorders/PAD01.001499877.PRIMO.xml +227 -0
  172. data/test/mab_files/test_superorders/PAD01.001572048.PRIMO.xml +68 -0
  173. data/test/mab_files/test_title_display/PAD01.000954111.PRIMO.xml +162 -0
  174. data/test/mab_files/test_title_display/PAD01.000992332.PRIMO.xml +189 -0
  175. data/test/mab_files/test_title_display/PAD01.001015068.PRIMO.xml +216 -0
  176. data/test/mab_files/test_title_display/PAD01.001499879.PRIMO.xml +255 -0
  177. data/test/mab_files/test_title_search/test_1.xml +20 -0
  178. data/test/mab_files/test_title_sort/PAD01.000954111.PRIMO.xml +162 -0
  179. data/test/mab_files/test_title_sort/PAD01.000992332.PRIMO.xml +189 -0
  180. data/test/mab_files/test_volume_count_sort/PAD01.001015068.PRIMO.xml +216 -0
  181. data/test/mab_files/test_volume_count_sort/PAD01.001499879.PRIMO.xml +255 -0
  182. data/test/mabmapper/test_creation_date.rb +5 -0
  183. data/test/mabmapper/test_creationdate.rb +23 -0
  184. data/test/mabmapper/test_creator_contributor_facet.rb +4 -0
  185. data/test/mabmapper/test_description.rb +9 -0
  186. data/test/mabmapper/test_doc.rb +6 -0
  187. data/test/mabmapper/test_edition.rb +8 -0
  188. data/test/mabmapper/test_erscheinungsform.rb +5 -0
  189. data/test/mabmapper/test_ht_number.rb +4 -0
  190. data/test/mabmapper/test_inhaltstyp.rb +5 -0
  191. data/test/mabmapper/test_is_secondary_form.rb +7 -0
  192. data/test/mabmapper/test_is_suborder.rb +7 -0
  193. data/test/mabmapper/test_issn.rb +4 -0
  194. data/test/mabmapper/test_materialtyp.rb +5 -0
  195. data/test/mabmapper/test_notation_sort.rb +5 -0
  196. data/test/mabmapper/test_publisher.rb +5 -0
  197. data/test/mabmapper/test_redactional_remark.rb +4 -0
  198. data/test/mabmapper/test_relation.rb +16 -0
  199. data/test/mabmapper/test_secondary_form_creationdate.rb +6 -0
  200. data/test/mabmapper/test_secondary_form_isbn.rb +6 -0
  201. data/test/mabmapper/test_secondary_form_physical_description.rb +5 -0
  202. data/test/mabmapper/test_secondary_form_preliminary_phrase.rb +5 -0
  203. data/test/mabmapper/test_secondary_form_publisher.rb +5 -0
  204. data/test/mabmapper/test_secondary_form_superorder.rb +9 -0
  205. data/test/mabmapper/test_short_title_display.rb +27 -0
  206. data/test/mabmapper/test_signature.rb +12 -0
  207. data/test/mabmapper/test_signature_search.rb +12 -0
  208. data/test/mabmapper/test_status.rb +13 -0
  209. data/test/mabmapper/test_subject.rb +5 -0
  210. data/test/mabmapper/test_suborders.rb +192 -0
  211. data/test/mabmapper/test_superorder.rb +7 -0
  212. data/test/mabmapper/test_superorder_display.rb +22 -0
  213. data/test/mabmapper/test_superorders.rb +38 -0
  214. data/test/mabmapper/test_title_display.rb +12 -0
  215. data/test/mabmapper/test_title_search.rb +4 -0
  216. data/test/mabmapper/test_title_sort.rb +6 -0
  217. data/test/mabmapper/test_volume_count_sort.rb +5 -0
  218. data/test/test_helper.rb +53 -0
  219. data/test/test_mabmapper.rb +19 -0
  220. data/utils/mab_by_docid.sh +19 -0
  221. metadata +574 -0
checksums.yaml ADDED
@@ -0,0 +1,7 @@
1
+ ---
2
+ SHA1:
3
+ metadata.gz: edfa34f2b352b77bf53e7f581e3d60e8c59c84bf
4
+ data.tar.gz: 4dad71a39bddd155c2c3595a0995278a882e67a1
5
+ SHA512:
6
+ metadata.gz: af04565ff5c6bd6fa406a124b865fd412353e3bae166cb798054cf79ec66e9632416269753539a5f3d2201f0c9831e30c702f31416d481efc6bde4392c3ecb7b
7
+ data.tar.gz: 8445b5bc982ee1254c110cf30b93508703c11b4d1f2d4dc6868b061fc7fd6bf86dffb18144d667d041c35940c35f06d36dc41ce5e960dfa474816b67e7701661
data/.gitignore ADDED
@@ -0,0 +1,20 @@
1
+ .DS_Store
2
+ .idea
3
+ *.gem
4
+ *.rbc
5
+ .bundle
6
+ .config
7
+ .yardoc
8
+ Gemfile.lock
9
+ InstalledFiles
10
+ _yardoc
11
+ coverage
12
+ doc/
13
+ lib/bundler/man
14
+ pkg
15
+ rdoc
16
+ spec/reports
17
+ test/tmp
18
+ test/version_tmp
19
+ tmp
20
+ testdata
data/.travis.yml ADDED
@@ -0,0 +1,4 @@
1
+ language: ruby
2
+ rvm:
3
+ - "1.9.3"
4
+ - "2.0.0"
data/Gemfile ADDED
@@ -0,0 +1,7 @@
1
+ source 'https://rubygems.org'
2
+
3
+ # needed by travis
4
+ gem 'rake'
5
+
6
+ # Specify your gem's dependencies in mabmapper.gemspec
7
+ gemspec
data/LICENSE ADDED
@@ -0,0 +1,22 @@
1
+ Copyright (c) 2012 René Sprotte
2
+
3
+ MIT License
4
+
5
+ Permission is hereby granted, free of charge, to any person obtaining
6
+ a copy of this software and associated documentation files (the
7
+ "Software"), to deal in the Software without restriction, including
8
+ without limitation the rights to use, copy, modify, merge, publish,
9
+ distribute, sublicense, and/or sell copies of the Software, and to
10
+ permit persons to whom the Software is furnished to do so, subject to
11
+ the following conditions:
12
+
13
+ The above copyright notice and this permission notice shall be
14
+ included in all copies or substantial portions of the Software.
15
+
16
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
17
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
18
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
19
+ NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
20
+ LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
21
+ OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
22
+ WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
data/README.md ADDED
@@ -0,0 +1,49 @@
1
+ # Mabmapper [![Build Status](https://travis-ci.org/ubpb/mabmapper.png)](https://travis-ci.org/ubpb/mabmapper) [![Dependencies](https://gemnasium.com/ubpb/mabmapper.png?travis)](https://gemnasium.com/ubpb/mabmapper) [![Code Climate](https://codeclimate.com/github/ubpb/mabmapper.png)](https://codeclimate.com/github/ubpb/mabmapper)
2
+
3
+ WARNING: This project is currently work in progress. Anything is subject to change.
4
+
5
+ Mabmapper is a powerful and extendable processing engine to normalize any kind of
6
+ input data into a simple intermediate format made of fields and values.
7
+
8
+ Mabmapper was created by René Sprotte for the Library of the University of Paderborn,
9
+ as part of an implementation project for a new search engine interface. It comes bundled
10
+ with a ready to use engine and a simple and powerful
11
+ [domain-specific language (DSL)](http://en.wikipedia.org/wiki/Domain-specific_language)
12
+ based on [Ruby](http://www.ruby-lang.org) to process MabXML files created by the
13
+ [Aleph Integrated Library System](http://www.exlibrisgroup.com/category/Aleph).
14
+ Hence the name Mabmapper.
15
+
16
+ Mabmapper is extadable and it is easy to create custom engines to process any kind of input data.
17
+
18
+ ## Why?
19
+
20
+ When working with heterogeneous data to feed into a search engine like [Primo](http://www.exlibrisgroup.com/category/PrimoOverview),
21
+ [Elastic Search](http://www.elasticsearch.org/) or [Solr](http://lucene.apache.org/solr/) it is often needed to
22
+ do some kind of data normalization to fit the data into a defined schema and/or to enrich the data. This is espacially true
23
+ when working with bibliographic data.
24
+
25
+ Some search solutions bundle normalization tools to deal with that problem. In case of Primo, the normalization is done
26
+ as part of the ingest workflow configured by a web based normalization rule editor. We find that approach
27
+ too cumbersome and inflexible to create and maintain complex normalization rules. This is where Mapmapper comes into play.
28
+
29
+ ## Installation
30
+
31
+ In a terminal install the gem by running
32
+
33
+ $ gem install mabmapper
34
+
35
+ ## Command line usage
36
+
37
+ Mabmapper provides the command line program `mabmapper`. In a terminal type
38
+
39
+ $ mabmapper --help
40
+
41
+ to explore how to use the program.
42
+
43
+ ## Contributing
44
+
45
+ 1. Fork it
46
+ 2. Create your feature branch (`git checkout -b my-new-feature`)
47
+ 3. Commit your changes (`git commit -am 'Added some feature'`)
48
+ 4. Push to the branch (`git push origin my-new-feature`)
49
+ 5. Create new Pull Request
data/Rakefile ADDED
@@ -0,0 +1,29 @@
1
+ #!/usr/bin/env rake
2
+ require "bundler/gem_tasks"
3
+ require "pry"
4
+ require "rake/testtask"
5
+ require "rubygems/package"
6
+
7
+ Rake::TestTask.new do |t|
8
+ t.pattern = "test/test_*.rb"
9
+ end
10
+
11
+ task :create_mab_test_files_tar_gz do
12
+ mab_file_names = Dir.glob(File.expand_path('../test/mab_files', __FILE__) + '/**/PAD01.*.PRIMO.xml')
13
+ tar_gz_file_name = File.join(File.expand_path('..', __FILE__), 'mab_test_files.tar.gz')
14
+ gzip_writer = Zlib::GzipWriter.new(File.open(tar_gz_file_name, "w"))
15
+ tar_gz_writer = Gem::Package::TarWriter.new(gzip_writer)
16
+
17
+ mab_file_names.each do |mab_file_name|
18
+ mab_file_content = File.read(mab_file_name)
19
+
20
+ tar_gz_writer.add_file_simple(File.basename(mab_file_name), 0644, mab_file_content.bytesize) do |f|
21
+ f.write mab_file_content
22
+ end
23
+ end
24
+
25
+ tar_gz_writer.close
26
+ gzip_writer.close
27
+ end
28
+
29
+ task :default => :test
data/bin/mabmapper ADDED
@@ -0,0 +1,3 @@
1
+ #!/usr/bin/env ruby
2
+ require 'mabmapper'
3
+ Mabmapper::Cli.new