blacklight-marc 6.1.1 → 7.0.1

Sign up to get free protection for your applications and to get access to all the features.
Files changed (49) hide show
  1. checksums.yaml +5 -5
  2. data/.travis.yml +10 -4
  3. data/Gemfile +12 -0
  4. data/README.md +28 -7
  5. data/Rakefile +0 -2
  6. data/app/assets/stylesheets/blacklight_marc.scss +4 -6
  7. data/app/helpers/blacklight_marc_helper.rb +5 -4
  8. data/app/models/concerns/blacklight/solr/document/marc.rb +13 -12
  9. data/app/models/concerns/blacklight/solr/document/marc_export.rb +53 -50
  10. data/app/views/bookmarks/_endnote.html.erb +1 -1
  11. data/app/views/bookmarks/_refworks.html.erb +1 -1
  12. data/app/views/catalog/_marc_view.html.erb +4 -4
  13. data/app/views/catalog/endnote.endnote.erb +1 -1
  14. data/app/views/catalog/librarian_view.html.erb +7 -4
  15. data/blacklight-marc.gemspec +7 -10
  16. data/config/routes.rb +1 -1
  17. data/lib/blacklight/marc/catalog.rb +9 -15
  18. data/lib/blacklight/marc/engine.rb +2 -0
  19. data/lib/blacklight/marc/indexer.rb +9 -39
  20. data/lib/blacklight/marc/indexer/formats.rb +13 -15
  21. data/lib/blacklight/marc/routes.rb +2 -39
  22. data/lib/blacklight/marc/routes/marc_viewable.rb +20 -0
  23. data/lib/blacklight/marc/version.rb +1 -1
  24. data/lib/generators/blacklight/marc/install_generator.rb +15 -8
  25. data/lib/generators/blacklight/marc/templates/app/models/marc_indexer.rb +59 -59
  26. data/lib/generators/blacklight/marc/templates/config/translation_maps/callnumber_map.properties +149 -11
  27. data/lib/railties/solr_marc.rake +33 -33
  28. data/solr/conf/schema.xml +326 -573
  29. data/solr/conf/solrconfig.xml +78 -294
  30. data/spec/controllers/catalog_controller_spec.rb +11 -6
  31. data/spec/features/bookmarks_spec.rb +2 -1
  32. data/spec/features/search_formats_spec.rb +3 -3
  33. data/spec/integration/solr_document_spec.rb +19 -19
  34. data/spec/lib/blacklight_solr_document_marc_spec.rb +7 -7
  35. data/spec/lib/indexer/dewey_spec.rb +4 -4
  36. data/spec/lib/indexer/formats_spec.rb +9 -1
  37. data/spec/lib/marc_export_spec.rb +46 -46
  38. data/spec/lib/tasks/solr_marc_task_spec.rb +7 -7
  39. data/spec/lib/traject_indexer_spec.rb +6 -2
  40. data/spec/routing/routes_spec.rb +0 -6
  41. data/spec/test_app_templates/Gemfile.extra +2 -0
  42. data/spec/test_app_templates/lib/generators/test_app_generator.rb +14 -13
  43. data/spec/views/bookmarks/_endnote.html.erb_spec.rb +16 -6
  44. data/spec/views/bookmarks/_refworks.html.erb_spec.rb +17 -7
  45. data/spec/views/catalog/index.atom.builder_spec.rb +12 -17
  46. data/test_support/config/translation_maps/test_formats.properties +3 -1
  47. metadata +23 -43
  48. data/app/helpers/blacklight_bookmarks_helper.rb +0 -3
  49. data/solr/sample_solr_documents.yml +0 -2692
@@ -48,15 +48,15 @@ DG = DG - Italy (History)
48
48
  DH = DH - Low Countries (History)
49
49
  DJK = DJK - Eastern Europe (History)
50
50
  DJ = DJ - Netherlands (History)
51
- DK = DK - Russia. Former Soviet Republics. Poland (History)
51
+ DK = DK - Russia. Former Soviet Republics. Poland (History)
52
52
  DL = DL - Scandinavia (History)
53
53
  DP = DP - Spain. Portugal (History)
54
54
  DQ = DQ - Switzerland (History)
55
55
  DR = DR - Balkan Peninsula (History)
56
56
  DS = DS - Asia (History)
57
57
  DT = DT - Africa (History)
58
- DU = DU - Oceanía (History)
59
- DX = DX - Gypsies (History)
58
+ DU = DU - Oceania (History)
59
+ DX = DX - Romanies (History)
60
60
  D = D - World History
61
61
  E = E - History of the Americas (General)
62
62
  F = F - History of the Americas (Local)
@@ -80,7 +80,7 @@ HG = HG - Finance
80
80
  HJ = HJ - Public Finance
81
81
  HM = HM - Sociology
82
82
  HN = HN - Social History & Conditions
83
- HQ = HQ - The Family, Marriage, Woman
83
+ HQ = HQ - The Family, Marriage, Women
84
84
  HS = HS - Societies
85
85
  HT = HT - Communities, Classes, Races
86
86
  HV = HV - Social Pathology, Social & Public Welfare, Criminology
@@ -106,13 +106,54 @@ KB = KB - Religious Law (General)
106
106
  KDC = KDC - Law of Scotland
107
107
  KDE = KDE - Law of Northern Ireland
108
108
  KDG = KDG - Law of Isle of Man, Channel Islands
109
- KDK = KDK - Law of Ireland (EIRE)
109
+ KDK = KDK - Law of Ireland (Eire)
110
110
  KDZ = KDZ - Law of America, North America
111
111
  KD = KD - Law of England & Wales
112
112
  KE = KE - Law of Canada
113
113
  KF = KF - Law of the U.S.
114
+ KGA = KGA - Law of Belize
115
+ KGB = KGB - Law of Costa Rica
116
+ KGC = KGC - Law of El Salvador
117
+ KGD = KGD - Law of Guatemala
118
+ KGE = KGE - Law of Honduras
119
+ KGF = KGF - Law of Mexico
120
+ KGG = KGG - Law of Nicaragua
121
+ KGH = KGH - Law of Panama, Panama Canal Zone
122
+ KGJ = KGJ - Law of West Indies, Caribbean area (General), Anguilla
123
+ KGK = KGK - Law of Antigua and Barbuda, Aruba
124
+ KGL = KGL - Law of Bahamas, Barbados, Bonaire, British Leeward Islands, British Virgin Islands, British West Indies, British Windward Islands
125
+ KGM = KGM - Law of Cayman Islands
126
+ KGN = KGN - Law of Cuba
127
+ KGP = KGP - Law of Curaçao, Dominica
128
+ KGQ = KGQ - Law of Dominican Republic
129
+ KGR = KGR - Law of Dutch Leeward Islands (General), Dutch West Indies (Netherlands Antilles), Dutch Windward Islands (General), French West Indies (General), Grenada, Guadeloupe
130
+ KGS = KGS - Law of Haiti
131
+ KGT = KGT - Law of Jamaica, Martinique, Montserrat
132
+ KGU = KGU - Law of Navassa Islands
133
+ KGV = KGV - Law of Puerto Rico
134
+ KGW = KGW - Law of Saba, Saint Christopher (Saint Kitts), Nevis, and Anguilla, Saint Lucia, Saint Vincent and the Grenadines, Sint Eustatius, Sint Maarten
135
+ KGX = KGX - Law of Trinidad and Tobago
136
+ KGY = KGY - Law of Turks and Caicos Islands
137
+ KGZ = KGZ - Law of Virgin Islands of the United States
114
138
  KG = KG - Law of Latin America, Mexico, Central America, West Indies, Caribbean
115
- KH = KH - South America
139
+ KHA = KHA - Law of Argentina
140
+ KHC = KHC - Law of Bolivia
141
+ KHD = KHD - Law of Brazil
142
+ KHF = KHF - Law of Chile
143
+ KHH = KHH - Law of Colombia
144
+ KHK = KHK - Law of Ecuador
145
+ KHL = KHL - Law of Falkland Islands
146
+ KHM = KHM - Law of French Guiana
147
+ KHN = KHN - Law of Guyana
148
+ KHP = KHP - Law of Paraguay
149
+ KHQ = KHQ - Law of Peru
150
+ KHS = KHS - Law of Surinam
151
+ KHU = KHU - Law of Uruguay
152
+ KHW = KHW - Law of Venezuela
153
+ KH = KH - Law of South America
154
+ KIM = KIM - Indigenous law: Central & South America
155
+ KIN = KIN - Indigenous law: Honduras
156
+ KIP = KIP - Indigenous law: Nicaragua
116
157
  KJA = KJA - Roman Law
117
158
  KJC = KJC - Regional Comparative & Uniform Law
118
159
  KJE = KJE - Regional Organization & Integration
@@ -154,7 +195,7 @@ KLA = KLA - Law of Russia, Soviet Union
154
195
  KLB = KLB - Law of Russia (Federation)
155
196
  KLD = KLD - Law of Armenia (Republic)
156
197
  KLE = KLE - Law of Azerbaijan
157
- KLF = KLF - Law of Belarus
198
+ KLF = KLF - Law of Belarus
158
199
  KLH = KLH - Law of Georgia
159
200
  KLM = KLM - Law of Moldova
160
201
  KLP = KLP - Law of Ukraine
@@ -169,7 +210,7 @@ KMH = KMH - Law of Iran
169
210
  KMJ = KMJ - Law of Iraq
170
211
  KMK = KMK - Law of Israel
171
212
  KML = KML - Law of Jerusalem
172
- KMM = KMM - Law of Jordan
213
+ KMM = KMM - Law of Jordan, West Bank
173
214
  KMN = KMN - Law of Kuwait
174
215
  KMP = KMP - Law of Lebanon
175
216
  KMT = KMT - Law of Saudi Arabia
@@ -185,8 +226,105 @@ KNW = KNW - Law of Indonesia
185
226
  KNX = KNX - Law of Japan
186
227
  KPA = KPA - Law of Korea, South Korea
187
228
  KPC = KPC - Law of Korea, North Korea
188
- KQ = KQ - Law of Africa
189
- KU = KU - Law of the Pacific Area, Australia, New Zealand
229
+ KQG = KQG - Law of Algeria
230
+ KQH = KQH - Law of Angola
231
+ KQJ = KQJ - Law of Benin
232
+ KQK = KQK - Law of Botswana
233
+ KQM = KQM - Law of the British Central Africa Protectorate
234
+ KQP = KQP - Law of British Indian Ocean Territory, British Somaliland
235
+ KQT = KQT - Law of Burkina Faso
236
+ KQV = KQV - Law of Burundi
237
+ KQW = KQW - Law of Cameroon
238
+ KQX = KQX - Law of Cape Verde
239
+ KQ = KQ - Law of Africa (Algeria to Cape Verde)
240
+ KRB = KRB - Law of Central African Republic
241
+ KRC = KRC - Law of Chad
242
+ KRE = KRE - Law of Comoros
243
+ KRG = KRG - Law of Congo
244
+ KRK = KRK - Law of Djibouti
245
+ KRL = KRL - Law of East Africa Protectorate
246
+ KRM = KRM - Law of Egypt
247
+ KRN = KRN - Law of Eritrea
248
+ KRP = KRP - Law of Ethiopia
249
+ KRR = KRR - Law of French Equatorial Africa
250
+ KRS = KRS - Law of French West Africa
251
+ KRU = KRU - Law of Gabon
252
+ KRV = KRV - Law of Gambia
253
+ KRW = KRW - Law of German East Africa
254
+ KRX = KRX - Law of Ghana
255
+ KRY = KRY - Law of Gibraltar
256
+ KR = KR - Law of Africa (Central African Republic to Gibraltar)
257
+ KSA = KSA - Law of Guinea
258
+ KSC = KSC - Law of Guinea-Bissau
259
+ KSE = KSE - Law of Equatorial Guinea, Ifni
260
+ KSG = KSG - Law of Italian East Africa, Italian Somaliland
261
+ KSH = KSH - Law of Ivory Coast
262
+ KSK = KSK - Law of Kenya
263
+ KSL = KSL - Law of Lesotho
264
+ KSN = KSN - Law of Liberia
265
+ KSP = KSP - Law of Libya
266
+ KSR = KSR - Law of Madagascar
267
+ KSS = KSS - Law of Malawi
268
+ KST = KST - Law of Mali
269
+ KSU = KSU - Law of Mauritania
270
+ KSV = KSV - Law of Mauritius
271
+ KSV = KSV - Law of Mayotte
272
+ KSW = KSW - Law of Morocco
273
+ KSX = KSX - Law of Mozambique
274
+ KSY = KSY - Law of Namibia
275
+ KSZ = KSZ - Law of Niger
276
+ KS = KS - Law of Africa (Guinea to Niger)
277
+ KTA = KTA - Law of Nigeria
278
+ KTC = KTC - Law of Réunion
279
+ KTD = KTD - Law of Rwanda
280
+ KTE = KTE - Law of Saint Helena
281
+ KTF = KTF - Law of São Tomé and Principe
282
+ KTG = KTG - Law of Senegal
283
+ KTH = KTH - Law of Seychelles
284
+ KTJ = KTJ - Law of Sierra Leone
285
+ KTK = KTK - Law of Somalia
286
+ KTL = KTL - Law of South Africa, Republic of
287
+ KTN = KTN - Law of Spanish West Africa (to 1958), Spanish Sahara (to 1975)
288
+ KTQ = KTQ - Law of Sudan
289
+ KTR = KTR - Law of Swaziland
290
+ KTT = KTT - Law of Tanzania
291
+ KTU = KTU - Law of Togo
292
+ KTV = KTV - Law of Tunisia
293
+ KTW = KTW - Law of Uganda
294
+ KTX = KTX - Law of Zaire
295
+ KTY = KTY - Law of Zambia, Zanzibar (to 1964)
296
+ KTZ = KTZ - Law of Zimbabwe
297
+ KT = KT - Law of Africa (Nigeria to Zimbabwe)
298
+ KUQ = KUQ - Law of New Zealand
299
+ KU = KU - Law of Australia, Australian territories, New Zealand
300
+ KVB = KVB - Regional Comparative and Uniform Law of Australia and New Zealand
301
+ KVC = KVC - Regional Comparative and Uniform Law of Other Pacific area jurisdictions
302
+ KVE = KVE - Regional organization and integration (Pacific Area)
303
+ KVH = KVH - Law of American Samoa, British New Guinea (Territory of Papua)
304
+ KVL = KVL - Law of Cook Islands
305
+ KVM = KVM - Law of Easter Island
306
+ KVN = KVN - Law of Fiji
307
+ KVP = KVP - Law of French Polynesia
308
+ KVP = KVP - Law of German New Guinea (to 1914)
309
+ KVQ = KVQ - Law of Guam
310
+ KVR = KVR - Law of Kiribati
311
+ KVS = KVS - Law of Marshall Islands
312
+ KVS = KVS - Law of Micronesia (Federated States), Midway Islands
313
+ KVU = KVU - Law of Nauru, Netherlands New Guinea (to 1963)
314
+ KV = KV - Law of Asia and Eurasia, Africa, Pacific Area, and Antarctica
315
+ KVW = KVW - Law of New Caledonia
316
+ KWA = KWA - Law of Niue
317
+ KWC = KWC - Law of Northern Mariana Islands
318
+ KWE = KWE - Law of Pacific Islands (Trust Territory)
319
+ KWG = KWG - Law of Palau
320
+ KWH = KWH - Law of Papua New Guinea
321
+ KWL = KWL - Law of Pitcairn Island
322
+ KWL = KWL - Law of Solomon Islands
323
+ KWP = KWP - Law of Tonga
324
+ KWQ = KWQ - Law of Tuvalu
325
+ KWR = KWR - Law of Vanuatu
326
+ KWT = KWT - Law of Wake Island, Wallis and Futuna Islands
327
+ KWW = KWW - Law of Western Samoa
190
328
  KWX = KWX - Law of Antarctica
191
329
  KZ = KZ - Law of Nations
192
330
  K = K - Law
@@ -230,7 +368,7 @@ PQ = PQ - French, Italian, Spanish & Portuguese Literature
230
368
  PR = PR - English Literature
231
369
  PS = PS - American Literature
232
370
  PT = PT - Germanic & Scandinavian Literatures
233
- PZ = PZ - Childrens Literature
371
+ PZ = PZ - Children's Literature
234
372
  P = P - Language & Literature
235
373
  QA = QA - Mathematics
236
374
  QB = QB - Astronomy
@@ -24,28 +24,28 @@ module SolrMarc
24
24
  end
25
25
  namespace :solr do
26
26
  namespace :marc do
27
-
28
-
27
+
28
+
29
29
  desc "Index the supplied test data into Solr"
30
30
  task :index_test_data => :environment do
31
- # for now we are assuming test data is located in BL source checkout.
31
+ # for now we are assuming test data is located in BL source checkout.
32
32
  ENV['MARC_FILE'] = File.expand_path("../../../test_support/data/test_data.utf8.mrc", __FILE__ )
33
-
34
- # solr_path and solr_war_path will be picked up from
35
- # jetty_path in solr.yml by main work task.
36
-
33
+
34
+ # solr_path and solr_war_path will be picked up from
35
+ # jetty_path in solr.yml by main work task.
36
+
37
37
  Rake::Task[ "solr:marc:index:work" ].invoke
38
38
  end
39
-
39
+
40
40
  desc "Index marc data using SolrMarc. Available environment variables: MARC_RECORDS_PATH, CONFIG_PATH, SOLR_MARC_MEM_ARGS"
41
41
  task :index => "index:work"
42
42
  namespace :index do
43
43
 
44
44
  task :work => :environment do
45
- solrmarc_arguments = compute_arguments
45
+ solrmarc_arguments = compute_arguments
46
46
 
47
47
  # If no marc records given, display :info task
48
- if (ENV["NOOP"] || (!solrmarc_arguments["MARC_FILE"]))
48
+ if (ENV["NOOP"] || (!solrmarc_arguments["MARC_FILE"]))
49
49
  Rake::Task[ "solr:marc:index:info" ].execute
50
50
  else
51
51
  require './app/models/marc_indexer' unless defined?(MarcIndexer)
@@ -53,29 +53,29 @@ namespace :solr do
53
53
  SolrMarc.indexer.process(io)
54
54
  end
55
55
  end
56
-
56
+
57
57
  end # work
58
-
58
+
59
59
  desc "Shows more info about the solr:marc:index task."
60
60
  task :info do
61
61
  solrmarc_arguments = compute_arguments
62
62
  puts <<-EOS
63
- Solr to write to is taken from current environment in config/solr.yml,
63
+ Solr to write to is taken from current environment in config/solr.yml,
64
64
  key :replicate_master_url is supported, taking precedence over :url
65
- for where to write to.
66
-
65
+ for where to write to.
66
+
67
67
  Possible environment variables, with settings as invoked. You can set these
68
68
  variables on the command line, eg:
69
69
  rake solr:marc:index MARC_FILE=/some/file.mrc
70
-
70
+
71
71
  MARC_FILE: #{solrmarc_arguments["MARC_FILE"] || "[marc records path needed]"}
72
-
72
+
73
73
  CONFIG_PATH: #{solrmarc_arguments[:config_properties_path]}
74
74
  Defaults to RAILS_ROOT/config/SolrMarc/config(-RAILS_ENV).properties
75
75
  or else RAILS_ROOT/vendor/plugins/blacklight/SolrMarc/config ...
76
76
 
77
77
  Note that SolrMarc search path includes directory of config_path,
78
- so translation_maps and index_scripts dirs will be found there.
78
+ so translation_maps and index_scripts dirs will be found there.
79
79
  EOS
80
80
  end
81
81
  end # index
@@ -85,14 +85,14 @@ end # :solr
85
85
  # Computes arguments to Solr, returns hash
86
86
  # Calculate default args based on location of rake file itself,
87
87
  # which we assume to be in the plugin, or in the Rails executing
88
- # this rake task, at RAILS_ROOT.
88
+ # this rake task, at RAILS_ROOT.
89
89
  def compute_arguments
90
-
90
+
91
91
  arguments = {}
92
92
 
93
93
  arguments["MARC_FILE"] = ENV["MARC_FILE"]
94
94
 
95
-
95
+
96
96
  arguments[:config_properties_path] = ENV['CONFIG_PATH']
97
97
 
98
98
 
@@ -112,39 +112,39 @@ def compute_arguments
112
112
  end
113
113
  end
114
114
  end
115
-
115
+
116
116
  #java mem arg is from env, or default
117
117
 
118
118
  arguments[:solrmarc_mem_arg] = ENV['SOLRMARC_MEM_ARGS'] || '-Xmx512m'
119
-
119
+
120
120
  # SolrMarc is embedded in the plugin, or could be a custom
121
- # one in local app.
122
- arguments[:solrmarc_jar_path] = ENV['SOLRMARC_JAR_PATH'] || locate_path("lib", "SolrMarc.jar")
123
-
121
+ # one in local app.
122
+ arguments[:solrmarc_jar_path] = ENV['SOLRMARC_JAR_PATH'] || locate_path("lib", "SolrMarc.jar")
123
+
124
+
124
125
 
125
-
126
126
  # solrmarc.solr.war.path and solr.path, for now pull out of ENV
127
- # if present. In progress. jrochkind 25 Apr 2011.
127
+ # if present. In progress. jrochkind 25 Apr 2011.
128
128
  arguments[:solr_war_path] = ENV["SOLR_WAR_PATH"] if ENV["SOLR_WAR_PATH"]
129
129
  arguments[:solr_path] = ENV['SOLR_PATH'] if ENV['SOLR_PATH']
130
130
 
131
131
  # Solr URL, find from solr.yml, app or plugin
132
132
  # use :replicate_master_url for current env if present, otherwise :url
133
- # for current env.
134
- # Also take jetty_path from there if present.
133
+ # for current env.
134
+ # Also take jetty_path from there if present.
135
135
  if c = Blacklight.connection_config
136
- arguments[:solr_url] = c[:url]
136
+ arguments[:solr_url] = c[:url]
137
137
  if c[:jetty_path]
138
138
  arguments[:solr_path] ||= File.expand_path(File.join(c[:jetty_path], "solr"), Rails.root)
139
139
  arguments[:solr_war_path] ||= File.expand_path(File.join(c[:jetty_path], "webapps", "solr.war"), Rails.root)
140
140
  end
141
141
  end
142
-
142
+
143
143
  return arguments
144
144
  end
145
145
 
146
146
  def locate_path(*subpath_fragments)
147
- local_root = File.expand_path File.join(File.dirname(__FILE__), '..', '..')
147
+ local_root = File.expand_path File.join(File.dirname(__FILE__), '..', '..')
148
148
  subpath = subpath_fragments.join('/')
149
149
  base_match = [Rails.root, local_root].find do |base|
150
150
  File.exists? File.join(base, subpath)
data/solr/conf/schema.xml CHANGED
@@ -1,306 +1,348 @@
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 the Solr schema file. This file should be named "schema.xml" and
21
- should be in the conf directory under the solr home
22
- (i.e. ./solr/conf/schema.xml by default)
23
- or located where the classloader for the Solr webapp can find it.
24
-
25
- This example schema is the recommended starting point for users.
26
- It should be kept correct and concise, usable out-of-the-box.
27
-
28
- For more information, on how to customize this file, please see
29
- http://wiki.apache.org/solr/SchemaXml
30
-
31
- PERFORMANCE NOTE: this schema includes many optional features and should not
32
- be used for benchmarking. To improve performance one could
33
- - set stored="false" for all fields possible (esp large fields) when you
34
- only need to search on the field but don't need to return the original
35
- value.
36
- - set indexed="false" if you don't need to search on the field, but only
37
- return the field as a result of searching on other indexed fields.
38
- - remove all unneeded copyField statements
39
- - for best index size and searching performance, set "index" to false
40
- for all general text fields, use copyField to copy them to the
41
- catchall "text" field, and use that for searching.
42
- - For maximum indexing performance, use the StreamingUpdateSolrServer
43
- java client.
44
- - Remember to run the JVM in server mode, and use a higher logging level
45
- that avoids logging every request
46
- -->
47
-
48
- <schema name="Blacklight Demo Index" version="1.5">
49
- <!-- attribute "name" is the name of this schema and is only used for display purposes.
50
- Applications should change this to reflect the nature of the search collection.
51
- version="1.4" is Solr's version number for the schema syntax and semantics. It should
52
- not normally be changed by applications.
53
- 1.0: multiValued attribute did not exist, all fields are multiValued by nature
54
- 1.1: multiValued attribute introduced, false by default
55
- 1.2: omitTermFreqAndPositions attribute introduced, true by default except for text fields.
56
- 1.3: removed optional field compress feature
57
- 1.4: default auto-phrase (QueryParser feature) to off
58
- -->
1
+ <?xml version="1.0" encoding="UTF-8"?>
2
+ <schema name="Hydra" version="1.5">
3
+ <!-- NOTE: various comments and unused configuration possibilities have been purged
4
+ from this file. Please refer to http://wiki.apache.org/solr/SchemaXml,
5
+ as well as the default schema file included with Solr -->
59
6
 
60
- <types>
61
- <!-- field type definitions. The "name" attribute is
62
- just a label to be used by field definitions. The "class"
63
- attribute and any other attributes determine the real
64
- behavior of the fieldType.
65
- Class names starting with "solr" refer to java classes in the
66
- org.apache.solr.analysis package.
67
- -->
7
+ <uniqueKey>id</uniqueKey>
68
8
 
69
- <!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
70
- <fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
71
-
72
- <!-- boolean type: "true" or "false" -->
73
- <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
74
- <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
75
- <fieldtype name="binary" class="solr.BinaryField"/>
76
-
77
- <!-- The optional sortMissingLast and sortMissingFirst attributes are
78
- currently supported on types that are sorted internally as strings
79
- and on numeric types.
80
- This includes "string","boolean", and, as of 3.5 (and 4.x),
81
- int, float, long, date, double, including the "Trie" variants.
82
- - If sortMissingLast="true", then a sort on this field will cause documents
83
- without the field to come after documents with the field,
84
- regardless of the requested sort order (asc or desc).
85
- - If sortMissingFirst="true", then a sort on this field will cause documents
86
- without the field to come before documents with the field,
87
- regardless of the requested sort order.
88
- - If sortMissingLast="false" and sortMissingFirst="false" (the default),
89
- then default lucene sorting will be used which places docs without the
90
- field first in an ascending sort and last in a descending sort.
91
- -->
92
-
93
- <!--
94
- Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
95
- -->
96
- <fieldType name="int" class="solr.TrieIntField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
97
- <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
98
- <fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
99
- <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
100
-
101
- <!--
102
- Numeric field types that index each value at various levels of precision
103
- to accelerate range queries when the number of values between the range
104
- endpoints is large. See the javadoc for NumericRangeQuery for internal
105
- implementation details.
106
-
107
- Smaller precisionStep values (specified in bits) will lead to more tokens
108
- indexed per value, slightly larger index size, and faster range queries.
109
- A precisionStep of 0 disables indexing at different precision levels.
110
- -->
111
- <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
112
- <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
113
- <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
114
- <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
115
-
116
- <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
117
- is a more restricted form of the canonical representation of dateTime
118
- http://www.w3.org/TR/xmlschema-2/#dateTime
119
- The trailing "Z" designates UTC time and is mandatory.
9
+ <fields>
10
+ <field name="id" type="string" stored="true" indexed="true" multiValued="false" required="true"/>
11
+ <field name="format" type="string" stored="true" indexed="true" multiValued="true" />
12
+ <field name="_version_" type="long" indexed="true" stored="true"/>
13
+ <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
14
+
15
+ <field name="lat" type="tdouble" stored="true" indexed="true" multiValued="false"/>
16
+ <field name="lng" type="tdouble" stored="true" indexed="true" multiValued="false"/>
17
+ <!-- NOTE: not all possible Solr field types are represented in the dynamic fields -->
18
+
19
+ <!-- text (_t...) -->
20
+
21
+ <dynamicField name="*_ti" type="text" stored="false" indexed="true" multiValued="false"/>
22
+ <dynamicField name="*_tim" type="text" stored="false" indexed="true" multiValued="true"/>
23
+
24
+ <dynamicField name="*_ts" type="text" stored="true" indexed="false" multiValued="false"/>
25
+ <dynamicField name="*_tsm" type="text" stored="true" indexed="false" multiValued="true"/>
26
+ <dynamicField name="*_tsi" type="text" stored="true" indexed="true" multiValued="false"/>
27
+ <dynamicField name="*_tsim" type="text" stored="true" indexed="true" multiValued="true"/>
28
+
29
+ <dynamicField name="*_tiv" type="text" stored="false" indexed="true" multiValued="false" termVectors="true" termPositions="true" termOffsets="true"/>
30
+ <dynamicField name="*_timv" type="text" stored="false" indexed="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
31
+
32
+ <dynamicField name="*_tsiv" type="text" stored="true" indexed="true" multiValued="false" termVectors="true" termPositions="true" termOffsets="true"/>
33
+ <dynamicField name="*_tsimv" type="text" stored="true" indexed="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
34
+
35
+ <!-- English text (_te...) -->
36
+
37
+ <dynamicField name="*_tei" type="text_en" stored="false" indexed="true" multiValued="false"/>
38
+ <dynamicField name="*_teim" type="text_en" stored="false" indexed="true" multiValued="true"/>
39
+
40
+ <dynamicField name="*_tes" type="text_en" stored="true" indexed="false" multiValued="false"/>
41
+ <dynamicField name="*_tesm" type="text_en" stored="true" indexed="false" multiValued="true"/>
42
+ <dynamicField name="*_tesi" type="text_en" stored="true" indexed="true" multiValued="false"/>
43
+ <dynamicField name="*_tesim" type="text_en" stored="true" indexed="true" multiValued="true"/>
44
+
45
+ <dynamicField name="*_teiv" type="text_en" stored="false" indexed="true" multiValued="false" termVectors="true" termPositions="true" termOffsets="true"/>
46
+ <dynamicField name="*_teimv" type="text_en" stored="false" indexed="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
47
+
48
+ <dynamicField name="*_tesiv" type="text_en" stored="true" indexed="true" multiValued="false" termVectors="true" termPositions="true" termOffsets="true"/>
49
+ <dynamicField name="*_tesimv" type="text_en" stored="true" indexed="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
50
+
51
+ <!-- string (_s...) -->
52
+
53
+ <dynamicField name="*_si" type="string" stored="false" indexed="true" multiValued="false"/>
54
+ <dynamicField name="*_sim" type="string" stored="false" indexed="true" multiValued="true"/>
55
+
56
+ <dynamicField name="*_ss" type="string" stored="true" indexed="false" multiValued="false"/>
57
+ <dynamicField name="*_ssm" type="string" stored="true" indexed="false" multiValued="true"/>
58
+ <dynamicField name="*_ssi" type="string" stored="true" indexed="true" multiValued="false"/>
59
+ <dynamicField name="*_ssim" type="string" stored="true" indexed="true" multiValued="true"/>
60
+
61
+ <dynamicField name="*_ssort" type="alphaSort" stored="false" indexed="true" multiValued="false"/>
62
+
63
+
64
+ <!-- integer (_i...) -->
65
+
66
+ <dynamicField name="*_ii" type="int" stored="false" indexed="true" multiValued="false"/>
67
+ <dynamicField name="*_iim" type="int" stored="false" indexed="true" multiValued="true"/>
68
+
69
+ <dynamicField name="*_is" type="int" stored="true" indexed="false" multiValued="false"/>
70
+ <dynamicField name="*_ism" type="int" stored="true" indexed="false" multiValued="true"/>
71
+ <dynamicField name="*_isi" type="int" stored="true" indexed="true" multiValued="false"/>
72
+ <dynamicField name="*_isim" type="int" stored="true" indexed="true" multiValued="true"/>
73
+
74
+ <!-- IntegerPointField (_it...) (for faster range queries) -->
75
+
76
+ <dynamicField name="*_iti" type="tint" stored="false" indexed="true" multiValued="false"/>
77
+ <dynamicField name="*_itim" type="tint" stored="false" indexed="true" multiValued="true"/>
78
+
79
+ <dynamicField name="*_its" type="tint" stored="true" indexed="false" multiValued="false"/>
80
+ <dynamicField name="*_itsm" type="tint" stored="true" indexed="false" multiValued="true"/>
81
+ <dynamicField name="*_itsi" type="tint" stored="true" indexed="true" multiValued="false"/>
82
+ <dynamicField name="*_itsim" type="tint" stored="true" indexed="true" multiValued="true"/>
83
+
84
+ <!-- date (_dt...) -->
85
+ <!-- The format for this date field is of the form 1995-12-31T23:59:59Z
86
+ Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z -->
87
+
88
+ <dynamicField name="*_dti" type="date" stored="false" indexed="true" multiValued="false"/>
89
+ <dynamicField name="*_dtim" type="date" stored="false" indexed="true" multiValued="true"/>
90
+
91
+ <dynamicField name="*_dts" type="date" stored="true" indexed="false" multiValued="false"/>
92
+ <dynamicField name="*_dtsm" type="date" stored="true" indexed="false" multiValued="true"/>
93
+ <dynamicField name="*_dtsi" type="date" stored="true" indexed="true" multiValued="false"/>
94
+ <dynamicField name="*_dtsim" type="date" stored="true" indexed="true" multiValued="true"/>
95
+
96
+ <!-- DatePointField (_dtt...) (for faster range queries) -->
97
+
98
+ <dynamicField name="*_dtti" type="tdate" stored="false" indexed="true" multiValued="false"/>
99
+ <dynamicField name="*_dttim" type="tdate" stored="false" indexed="true" multiValued="true"/>
100
+
101
+ <dynamicField name="*_dtts" type="tdate" stored="true" indexed="false" multiValued="false"/>
102
+ <dynamicField name="*_dttsm" type="tdate" stored="true" indexed="false" multiValued="true"/>
103
+ <dynamicField name="*_dttsi" type="tdate" stored="true" indexed="true" multiValued="false"/>
104
+ <dynamicField name="*_dttsim" type="tdate" stored="true" indexed="true" multiValued="true"/>
105
+
106
+ <!-- long (_l...) -->
107
+
108
+ <dynamicField name="*_li" type="long" stored="false" indexed="true" multiValued="false"/>
109
+ <dynamicField name="*_lim" type="long" stored="false" indexed="true" multiValued="true"/>
110
+
111
+ <dynamicField name="*_ls" type="long" stored="true" indexed="false" multiValued="false"/>
112
+ <dynamicField name="*_lsm" type="long" stored="true" indexed="false" multiValued="true"/>
113
+ <dynamicField name="*_lsi" type="long" stored="true" indexed="true" multiValued="false"/>
114
+ <dynamicField name="*_lsim" type="long" stored="true" indexed="true" multiValued="true"/>
115
+
116
+ <!-- LongPointField (_lt...) (for faster range queries) -->
117
+
118
+ <dynamicField name="*_lti" type="tlong" stored="false" indexed="true" multiValued="false"/>
119
+ <dynamicField name="*_ltim" type="tlong" stored="false" indexed="true" multiValued="true"/>
120
+
121
+ <dynamicField name="*_lts" type="tlong" stored="true" indexed="false" multiValued="false"/>
122
+ <dynamicField name="*_ltsm" type="tlong" stored="true" indexed="false" multiValued="true"/>
123
+ <dynamicField name="*_ltsi" type="tlong" stored="true" indexed="true" multiValued="false"/>
124
+ <dynamicField name="*_ltsim" type="tlong" stored="true" indexed="true" multiValued="true"/>
125
+
126
+ <!-- double (_db...) -->
127
+
128
+ <dynamicField name="*_dbi" type="double" stored="false" indexed="true" multiValued="false"/>
129
+ <dynamicField name="*_dbim" type="double" stored="false" indexed="true" multiValued="true"/>
130
+
131
+ <dynamicField name="*_dbs" type="double" stored="true" indexed="false" multiValued="false"/>
132
+ <dynamicField name="*_dbsm" type="double" stored="true" indexed="false" multiValued="true"/>
133
+ <dynamicField name="*_dbsi" type="double" stored="true" indexed="true" multiValued="false"/>
134
+ <dynamicField name="*_dbsim" type="double" stored="true" indexed="true" multiValued="true"/>
135
+
136
+ <!-- DoublePointField (_dbt...) (for faster range queries) -->
137
+
138
+ <dynamicField name="*_dbti" type="tdouble" stored="false" indexed="true" multiValued="false"/>
139
+ <dynamicField name="*_dbtim" type="tdouble" stored="false" indexed="true" multiValued="true"/>
140
+
141
+ <dynamicField name="*_dbts" type="tdouble" stored="true" indexed="false" multiValued="false"/>
142
+ <dynamicField name="*_dbtsm" type="tdouble" stored="true" indexed="false" multiValued="true"/>
143
+ <dynamicField name="*_dbtsi" type="tdouble" stored="true" indexed="true" multiValued="false"/>
144
+ <dynamicField name="*_dbtsim" type="tdouble" stored="true" indexed="true" multiValued="true"/>
145
+
146
+ <!-- float (_f...) -->
147
+
148
+ <dynamicField name="*_fi" type="float" stored="false" indexed="true" multiValued="false"/>
149
+ <dynamicField name="*_fim" type="float" stored="false" indexed="true" multiValued="true"/>
150
+
151
+ <dynamicField name="*_fs" type="float" stored="true" indexed="false" multiValued="false"/>
152
+ <dynamicField name="*_fsm" type="float" stored="true" indexed="false" multiValued="true"/>
153
+ <dynamicField name="*_fsi" type="float" stored="true" indexed="true" multiValued="false"/>
154
+ <dynamicField name="*_fsim" type="float" stored="true" indexed="true" multiValued="true"/>
155
+
156
+ <!-- FloatPointField (_ft...) (for faster range queries) -->
157
+
158
+ <dynamicField name="*_fti" type="tfloat" stored="false" indexed="true" multiValued="false"/>
159
+ <dynamicField name="*_ftim" type="tfloat" stored="false" indexed="true" multiValued="true"/>
160
+
161
+ <dynamicField name="*_fts" type="tfloat" stored="true" indexed="false" multiValued="false"/>
162
+ <dynamicField name="*_ftsm" type="tfloat" stored="true" indexed="false" multiValued="true"/>
163
+ <dynamicField name="*_ftsi" type="tfloat" stored="true" indexed="true" multiValued="false"/>
164
+ <dynamicField name="*_ftsim" type="tfloat" stored="true" indexed="true" multiValued="true"/>
165
+
166
+ <!-- boolean (_b...) -->
167
+
168
+ <dynamicField name="*_bi" type="boolean" stored="false" indexed="true" multiValued="false"/>
169
+
170
+ <dynamicField name="*_bs" type="boolean" stored="true" indexed="false" multiValued="false"/>
171
+ <dynamicField name="*_bsi" type="boolean" stored="true" indexed="true" multiValued="false"/>
172
+
173
+ <!-- Type used to index the lat and lon components for the "location" FieldType -->
174
+
175
+ <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false" />
176
+
177
+
178
+ <!-- location (_ll...) -->
179
+
180
+ <dynamicField name="*_lli" type="location" stored="false" indexed="true" multiValued="false"/>
181
+ <dynamicField name="*_llim" type="location" stored="false" indexed="true" multiValued="true"/>
182
+
183
+ <dynamicField name="*_lls" type="location" stored="true" indexed="false" multiValued="false"/>
184
+ <dynamicField name="*_llsm" type="location" stored="true" indexed="false" multiValued="true"/>
185
+ <dynamicField name="*_llsi" type="location" stored="true" indexed="true" multiValued="false"/>
186
+ <dynamicField name="*_llsim" type="location" stored="true" indexed="true" multiValued="true"/>
187
+
188
+ <dynamicField name="*_srpt" type="location_rpt" stored="true" indexed="true" multiValued="true" />
189
+ <dynamicField name="*_bbox" type="bbox" stored="true" indexed="true" />
190
+
191
+
192
+ <!-- suggest and spelling -->
193
+ <dynamicField name="*spell" type="textSpell" indexed="true" stored="false" multiValued="true" />
194
+ <dynamicField name="*suggest" type="textSuggest" indexed="true" stored="false" multiValued="true" />
195
+
196
+ <!-- you must define copyField source and dest fields explicity or schemaBrowser doesn't work -->
197
+ <field name="all_text_timv" type="text" stored="false" indexed="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
198
+
199
+
200
+ </fields>
201
+
202
+
203
+ <!-- Above, multiple source fields are copied to the [text] field.
204
+ Another way to map multiple source fields to the same
205
+ destination field is to use the dynamic field syntax.
206
+ copyField also supports a maxChars to copy setting. -->
207
+
208
+ <copyField source="*_tsim" dest="all_text_timv" maxChars="3000"/>
209
+ <copyField source="*_tesim" dest="all_text_timv" maxChars="3000"/>
210
+ <copyField source="*_ssim" dest="all_text_timv" maxChars="3000"/>
211
+ <copyField source="*_si" dest="all_text_timv" maxChars="3000"/>
212
+
213
+ <copyField source="*_tsim" dest="suggest"/>
214
+ <copyField source="*_tesim" dest="suggest"/>
215
+ <copyField source="*_ssim" dest="suggest"/>
216
+ <copyField source="*_si" dest="suggest"/>
217
+
218
+ <!-- TODO: Look into if these are actually being used. -->
219
+ <copyField source="*_tsim" dest="spell"/>
220
+ <copyField source="*_tesim" dest="spell"/>
221
+ <copyField source="*_ssim" dest="spell"/>
222
+ <copyField source="*_si" dest="spell"/>
223
+
224
+ <copyField source="author_tsim" dest="author_spell"/>
225
+ <copyField source="subject_ssim" dest="subject_spell"/>
226
+ <copyField source="title_tsim" dest="title_spell"/>
227
+
228
+ <types>
229
+ <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
230
+ <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
231
+ <fieldType name="rand" class="solr.RandomSortField" omitNorms="true"/>
232
+
233
+ <!-- Default numeric field types. -->
234
+ <fieldType name="int" class="solr.IntPointField" docValues="true"/>
235
+ <fieldType name="float" class="solr.FloatPointField" docValues="true"/>
236
+ <fieldType name="long" class="solr.LongPointField" docValues="true"/>
237
+ <fieldType name="double" class="solr.DoublePointField" docValues="true"/>
238
+
239
+ <!-- PointField numeric field types for faster range queries -->
240
+ <fieldType name="tint" class="solr.IntPointField" docValues="true"/>
241
+ <fieldType name="tfloat" class="solr.FloatPointField" docValues="true"/>
242
+ <fieldType name="tlong" class="solr.LongPointField" docValues="true"/>
243
+ <fieldType name="tdouble" class="solr.DoublePointField" docValues="true"/>
244
+
245
+ <!-- The format for this date field is of the form 1995-12-31T23:59:59Z
120
246
  Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
121
- All other components are mandatory.
122
-
123
- Expressions can also be used to denote calculations that should be
124
- performed relative to "NOW" to determine the value, ie...
125
-
126
- NOW/HOUR
127
- ... Round to the start of the current hour
128
- NOW-1DAY
129
- ... Exactly 1 day prior to now
130
- NOW/DAY+6MONTHS+3DAYS
131
- ... 6 months and 3 days in the future from the start of
132
- the current day
133
-
134
- Consult the DateField javadocs for more information.
135
-
136
- Note: For faster range queries, consider the tdate type
137
247
  -->
138
- <fieldType name="date" class="solr.TrieDateField" omitNorms="true" precisionStep="0" positionIncrementGap="0"/>
139
-
140
- <!-- A Trie based date field for faster date range queries and date faceting. -->
141
- <fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" precisionStep="6" positionIncrementGap="0"/>
142
-
143
- <!-- The "RandomSortField" is not used to store or search any
144
- data. You can declare fields of this type it in your schema
145
- to generate pseudo-random orderings of your docs for sorting
146
- purposes. The ordering is generated based on the field name
147
- and the version of the index, As long as the index version
148
- remains unchanged, and the same field name is reused,
149
- the ordering of the docs will be consistent.
150
- If you want different psuedo-random orderings of documents,
151
- for the same version of the index, use a dynamicField and
152
- change the name
248
+ <fieldType name="date" class="solr.DatePointField" docValues="true"/>
249
+ <!-- A PointField based date field for faster date range queries and date faceting. -->
250
+ <fieldType name="tdate" class="solr.DatePointField" docValues="true"/>
251
+
252
+
253
+ <!-- This point type indexes the coordinates as separate fields (subFields)
254
+ If subFieldType is defined, it references a type, and a dynamic field
255
+ definition is created matching *___<typename>. Alternately, if
256
+ subFieldSuffix is defined, that is used to create the subFields.
257
+ Example: if subFieldType="double", then the coordinates would be
258
+ indexed in fields myloc_0___double,myloc_1___double.
259
+ Example: if subFieldSuffix="_d" then the coordinates would be indexed
260
+ in fields myloc_0_d,myloc_1_d
261
+ The subFields are an implementation detail of the fieldType, and end
262
+ users normally should not need to know about them.
153
263
  -->
154
- <fieldType name="random" class="solr.RandomSortField" indexed="true" />
264
+ <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
155
265
 
156
- <!-- solr.TextField allows the specification of custom text analyzers
157
- specified as a tokenizer and a list of token filters. Different
158
- analyzers may be specified for indexing and querying.
266
+ <!-- A specialized field for geospatial search filters and distance sorting. -->
267
+ <fieldType name="location" class="solr.LatLonPointSpatialField" docValues="true"/>
159
268
 
160
- The optional positionIncrementGap puts space between multiple fields of
161
- this type on the same document, with the purpose of preventing false phrase
162
- matching across fields.
269
+ <!-- An alternative geospatial field type new to Solr 4. It supports multiValued and polygon shapes.
270
+ For more information about this and other Spatial fields new to Solr 4, see:
271
+ http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
272
+ -->
273
+ <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
274
+ geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers"/>
163
275
 
164
- For more info on customizing your analyzer chain, please see
165
- http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
166
- -->
167
- <fieldType name="text" class="solr.TextField" positionIncrementGap="100">
168
- <analyzer>
169
- <tokenizer class="solr.StandardTokenizerFactory"/>
170
- <filter class="solr.ICUFoldingFilterFactory" />
171
- <filter class="solr.SnowballPorterFilterFactory" language="English" />
172
- </analyzer>
173
- </fieldType>
276
+ <field name="bbox" type="bbox" />
277
+ <fieldType name="bbox" class="solr.BBoxField"
278
+ geo="true" distanceUnits="kilometers" numberType="_bbox_coord" storeSubFields="false"/>
279
+ <fieldType name="_bbox_coord" class="solr.DoublePointField" docValues="true" stored="false"/>
174
280
 
175
- <!-- One can also specify an existing Analyzer class that has a
176
- default constructor via the class attribute on the analyzer element
177
- <fieldType name="text_greek" class="solr.TextField">
178
- <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
281
+ <fieldType name="text" class="solr.TextField" omitNorms="false">
282
+ <analyzer>
283
+ <tokenizer class="solr.ICUTokenizerFactory"/>
284
+ <filter class="solr.ICUFoldingFilterFactory"/> <!-- NFKC, case folding, diacritics removed -->
285
+ <filter class="solr.TrimFilterFactory"/>
286
+ </analyzer>
179
287
  </fieldType>
180
- -->
181
288
 
182
289
  <!-- A text field that only splits on whitespace for exact matching of words -->
183
290
  <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
184
291
  <analyzer>
185
292
  <tokenizer class="solr.WhitespaceTokenizerFactory"/>
293
+ <filter class="solr.TrimFilterFactory"/>
186
294
  </analyzer>
187
295
  </fieldType>
188
296
 
189
- <!-- A general text field that has reasonable, generic
190
- cross-language defaults: it tokenizes with StandardTokenizer,
191
- removes stop words from case-insensitive "stopwords.txt"
192
- (empty by default), and down cases. At query time only, it
193
- also applies synonyms. -->
194
- <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
195
- <analyzer type="index">
196
- <tokenizer class="solr.StandardTokenizerFactory"/>
197
- <!-- in this example, we will only use synonyms at query time
198
- <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
199
- -->
200
- <filter class="solr.LowerCaseFilterFactory"/>
201
- </analyzer>
202
- <analyzer type="query">
203
- <tokenizer class="solr.StandardTokenizerFactory"/>
204
- <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
205
- <filter class="solr.LowerCaseFilterFactory"/>
297
+ <!-- single token analyzed text, for sorting. Punctuation is significant. -->
298
+ <fieldtype name="alphaSort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
299
+ <analyzer>
300
+ <tokenizer class="solr.KeywordTokenizerFactory" />
301
+ <filter class="solr.ICUFoldingFilterFactory"/>
302
+ <filter class="solr.TrimFilterFactory" />
206
303
  </analyzer>
207
- </fieldType>
304
+ </fieldtype>
208
305
 
209
- <!-- A text field with defaults appropriate for English: it
210
- tokenizes with StandardTokenizer, removes English stop words
211
- (stopwords_en.txt), down cases, protects words from protwords.txt, and
212
- finally applies Porter's stemming. The query time analyzer
213
- also applies synonyms from synonyms.txt. -->
306
+ <!-- A text field with defaults appropriate for English -->
214
307
  <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
215
- <analyzer type="index">
216
- <tokenizer class="solr.StandardTokenizerFactory"/>
217
- <!-- in this example, we will only use synonyms at query time
218
- <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
219
- -->
220
- <filter class="solr.LowerCaseFilterFactory"/>
221
- <filter class="solr.EnglishPossessiveFilterFactory"/>
222
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
223
- <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
224
- <filter class="solr.EnglishMinimalStemFilterFactory"/>
225
- -->
226
- <filter class="solr.PorterStemFilterFactory"/>
227
- </analyzer>
228
- <analyzer type="query">
229
- <tokenizer class="solr.StandardTokenizerFactory"/>
230
- <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
231
- <filter class="solr.LowerCaseFilterFactory"/>
232
- <filter class="solr.EnglishPossessiveFilterFactory"/>
233
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
234
- <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
308
+ <analyzer>
309
+ <tokenizer class="solr.ICUTokenizerFactory"/>
310
+ <filter class="solr.ICUFoldingFilterFactory"/> <!-- NFKC, case folding, diacritics removed -->
311
+ <filter class="solr.EnglishPossessiveFilterFactory"/>
312
+ <!-- EnglishMinimalStemFilterFactory is less aggressive than PorterStemFilterFactory: -->
235
313
  <filter class="solr.EnglishMinimalStemFilterFactory"/>
236
- -->
314
+ <!--
237
315
  <filter class="solr.PorterStemFilterFactory"/>
316
+ -->
317
+ <filter class="solr.TrimFilterFactory"/>
238
318
  </analyzer>
239
319
  </fieldType>
240
320
 
241
- <!-- A text field with defaults appropriate for English, plus
242
- aggressive word-splitting and autophrase features enabled.
243
- This field is just like text_en, except it adds
244
- WordDelimiterFilter to enable splitting and matching of
245
- words on case-change, alpha numeric boundaries, and
246
- non-alphanumeric chars. This means certain compound word
247
- cases will work, for example query "wi fi" will match
248
- document "WiFi" or "wi-fi". However, other cases will still
249
- not match, for example if the query is "wifi" and the
250
- document is "wi fi" or if the query is "wi-fi" and the
251
- document is "wifi".
252
- -->
253
- <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
321
+ <!-- A text field with defaults appropriate for English an NGrams -->
322
+ <fieldType name="text_en_ng" class="solr.TextField" positionIncrementGap="100">
254
323
  <analyzer type="index">
255
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
256
- <!-- in this example, we will only use synonyms at query time
257
- <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
258
- -->
259
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
260
- <filter class="solr.LowerCaseFilterFactory"/>
261
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
262
- <filter class="solr.PorterStemFilterFactory"/>
263
- </analyzer>
264
- <analyzer type="query">
265
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
266
- <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
267
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
268
- <filter class="solr.LowerCaseFilterFactory"/>
269
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
270
- <filter class="solr.PorterStemFilterFactory"/>
324
+ <tokenizer class="solr.ICUTokenizerFactory"/>
325
+ <filter class="solr.ICUFoldingFilterFactory"/> <!-- NFKC, case folding, diacritics removed -->
326
+ <filter class="solr.EnglishPossessiveFilterFactory"/>
327
+ <!-- EnglishMinimalStemFilterFactory is less aggressive than PorterStemFilterFactory: -->
328
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>
329
+ <filter class="solr.TrimFilterFactory"/>
330
+ <filter class="solr.EdgeNGramFilterFactory" minGramSize="3" maxGramSize="15" />
271
331
  </analyzer>
272
- </fieldType>
273
332
 
274
- <!-- Less flexible matching, but less false matches. Probably not ideal for product names,
275
- but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
276
- <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
277
- <analyzer>
278
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
279
- <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
280
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_en.txt"/>
281
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
282
- <filter class="solr.LowerCaseFilterFactory"/>
283
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
333
+ <analyzer type="index">
334
+ <tokenizer class="solr.ICUTokenizerFactory"/>
335
+ <filter class="solr.ICUFoldingFilterFactory"/> <!-- NFKC, case folding, diacritics removed -->
336
+ <filter class="solr.EnglishPossessiveFilterFactory"/>
337
+ <!-- EnglishMinimalStemFilterFactory is less aggressive than PorterStemFilterFactory: -->
284
338
  <filter class="solr.EnglishMinimalStemFilterFactory"/>
285
- <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
286
- possible with WordDelimiterFilter in conjuncton with stemming. -->
287
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
339
+ <filter class="solr.TrimFilterFactory"/>
288
340
  </analyzer>
289
341
  </fieldType>
290
342
 
291
- <!-- Just like text_general except it reverses the characters of
292
- each token, to enable more efficient leading wildcard queries. -->
293
- <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
294
- <analyzer type="index">
295
- <tokenizer class="solr.StandardTokenizerFactory"/>
296
- <filter class="solr.LowerCaseFilterFactory"/>
297
- <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
298
- maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
299
- </analyzer>
300
- <analyzer type="query">
301
- <tokenizer class="solr.StandardTokenizerFactory"/>
302
- <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
303
- <filter class="solr.LowerCaseFilterFactory"/>
343
+ <fieldType name="pid_text" class="solr.TextField" positionIncrementGap="100">
344
+ <analyzer>
345
+ <tokenizer class="solr.KeywordTokenizerFactory"/>
304
346
  </analyzer>
305
347
  </fieldType>
306
348
 
@@ -308,328 +350,39 @@
308
350
  <analyzer>
309
351
  <tokenizer class="solr.StandardTokenizerFactory"/>
310
352
  <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
311
- <filter class="solr.StandardFilterFactory"/>
312
353
  <filter class="solr.LowerCaseFilterFactory"/>
313
354
  <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
314
355
  </analyzer>
315
356
  </fieldType>
316
357
 
317
- <fieldType class="solr.TextField" name="textSuggest" positionIncrementGap="100">
358
+ <fieldType name="textSuggest" class="solr.TextField" positionIncrementGap="100">
318
359
  <analyzer>
319
360
  <tokenizer class="solr.KeywordTokenizerFactory"/>
320
- <filter class="solr.StandardFilterFactory"/>
321
361
  <filter class="solr.LowerCaseFilterFactory"/>
322
362
  <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
323
363
  </analyzer>
324
364
  </fieldType>
325
365
 
326
- <!-- charFilter + WhitespaceTokenizer -->
327
- <!--
328
- <fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
329
- <analyzer>
330
- <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
331
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
366
+ <!-- queries for paths match documents at that path, or in descendent paths -->
367
+ <fieldType name="descendent_path" class="solr.TextField">
368
+ <analyzer type="index">
369
+ <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
332
370
  </analyzer>
333
- </fieldType>
334
- -->
335
-
336
- <!-- This is an example of using the KeywordTokenizer along
337
- With various TokenFilterFactories to produce a sortable field
338
- that does not include some properties of the source text
339
- -->
340
- <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
341
- <analyzer>
342
- <!-- KeywordTokenizer does no actual tokenizing, so the entire
343
- input string is preserved as a single token
344
- -->
345
- <tokenizer class="solr.KeywordTokenizerFactory"/>
346
- <!-- The LowerCase TokenFilter does what you expect, which can be
347
- when you want your sorting to be case insensitive
348
- -->
349
- <filter class="solr.LowerCaseFilterFactory" />
350
- <!-- The TrimFilter removes any leading or trailing whitespace -->
351
- <filter class="solr.TrimFilterFactory" />
352
- <!-- The PatternReplaceFilter gives you the flexibility to use
353
- Java Regular expression to replace any sequence of characters
354
- matching a pattern with an arbitrary replacement string,
355
- which may include back references to portions of the original
356
- string matched by the pattern.
357
-
358
- See the Java Regular Expression documentation for more
359
- information on pattern and replacement string syntax.
360
-
361
- http://java.sun.com/j2se/1.5.0/docs/api/java/util/regex/package-summary.html
362
- -->
363
- <filter class="solr.PatternReplaceFilterFactory"
364
- pattern="([^a-z])" replacement="" replace="all"
365
- />
371
+ <analyzer type="query">
372
+ <tokenizer class="solr.KeywordTokenizerFactory" />
366
373
  </analyzer>
367
374
  </fieldType>
368
-
369
- <fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
370
- <analyzer>
371
- <tokenizer class="solr.StandardTokenizerFactory"/>
372
- <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
373
- </analyzer>
374
- </fieldtype>
375
-
376
- <fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
377
- <analyzer>
378
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
379
- <!--
380
- The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
381
- a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
382
- Attributes of the DelimitedPayloadTokenFilterFactory :
383
- "delimiter" - a one character delimiter. Default is | (pipe)
384
- "encoder" - how to encode the following value into a playload
385
- float -> org.apache.lucene.analysis.payloads.FloatEncoder,
386
- integer -> o.a.l.a.p.IntegerEncoder
387
- identity -> o.a.l.a.p.IdentityEncoder
388
- Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
389
- -->
390
- <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
391
- </analyzer>
392
- </fieldtype>
393
375
 
394
- <!-- lowercases the entire field value, keeping it as a single token. -->
395
- <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
396
- <analyzer>
397
- <tokenizer class="solr.KeywordTokenizerFactory"/>
398
- <filter class="solr.LowerCaseFilterFactory" />
376
+ <!-- queries for paths match documents at that path, or in ancestor paths -->
377
+ <fieldType name="ancestor_path" class="solr.TextField">
378
+ <analyzer type="index">
379
+ <tokenizer class="solr.KeywordTokenizerFactory" />
399
380
  </analyzer>
400
- </fieldType>
401
-
402
- <fieldType name="text_path" class="solr.TextField" positionIncrementGap="100">
403
- <analyzer>
404
- <tokenizer class="solr.PathHierarchyTokenizerFactory"/>
381
+ <analyzer type="query">
382
+ <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
405
383
  </analyzer>
406
384
  </fieldType>
407
385
 
408
- <!-- since fields of this type are by default not stored or indexed,
409
- any data added to them will be ignored outright. -->
410
- <fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
411
-
412
- <!-- This point type indexes the coordinates as separate fields (subFields)
413
- If subFieldType is defined, it references a type, and a dynamic field
414
- definition is created matching *___<typename>. Alternately, if
415
- subFieldSuffix is defined, that is used to create the subFields.
416
- Example: if subFieldType="double", then the coordinates would be
417
- indexed in fields myloc_0___double,myloc_1___double.
418
- Example: if subFieldSuffix="_d" then the coordinates would be indexed
419
- in fields myloc_0_d,myloc_1_d
420
- The subFields are an implementation detail of the fieldType, and end
421
- users normally should not need to know about them.
422
- -->
423
- <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
424
-
425
- <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
426
- <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
427
-
428
- <!--
429
- A Geohash is a compact representation of a latitude longitude pair in a single field.
430
- See http://wiki.apache.org/solr/SpatialSearch
431
- -->
432
- <fieldtype name="geohash" class="solr.GeoHashField"/>
433
- </types>
434
-
435
-
436
- <fields>
437
- <!-- Valid attributes for fields:
438
- name: mandatory - the name for the field
439
- type: mandatory - the name of a previously defined type from the
440
- <types> section
441
- indexed: true if this field should be indexed (searchable or sortable)
442
- stored: true if this field should be retrievable
443
- multiValued: true if this field may contain multiple values per document
444
- omitNorms: (expert) set to true to omit the norms associated with
445
- this field (this disables length normalization and index-time
446
- boosting for the field, and saves some memory). Only full-text
447
- fields or fields that need an index-time boost need norms.
448
- termVectors: [false] set to true to store the term vector for a
449
- given field.
450
- When using MoreLikeThis, fields used for similarity should be
451
- stored for best performance.
452
- termPositions: Store position information with the term vector.
453
- This will increase storage costs.
454
- termOffsets: Store offset information with the term vector. This
455
- will increase storage costs.
456
- default: a value that should be used if no value is specified
457
- when adding a document.
458
- -->
459
-
460
- <!-- NOTE: this is not a full list of fields in the index; dynamic fields are also used -->
461
- <field name="id" type="string" indexed="true" stored="true" required="true" />
462
- <field name="_version_" type="long" indexed="true" stored="true" multiValued="false" />
463
- <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
464
- <!-- default, catch all search field -->
465
- <field name="text" type="text" indexed="true" stored="false" multiValued="true"/>
466
-
467
- <!-- these display fields are NOT multi-valued -->
468
- <field name="marc_display" type="string" indexed="false" stored="true" multiValued="false"/>
469
- <field name="title_display" type="string" indexed="false" stored="true" multiValued="false"/>
470
- <field name="title_vern_display" type="string" indexed="false" stored="true" multiValued="false"/>
471
- <field name="subtitle_display" type="string" indexed="false" stored="true" multiValued="false"/>
472
- <field name="subtitle_vern_display" type="string" indexed="false" stored="true" multiValued="false"/>
473
- <field name="author_display" type="string" indexed="false" stored="true" multiValued="false"/>
474
- <field name="author_vern_display" type="string" indexed="false" stored="true" multiValued="false"/>
475
-
476
- <!-- these fields are also used for display, so they must be stored -->
477
- <field name="isbn_t" type="text" indexed="true" stored="true" multiValued="true"/>
478
- <field name="language_facet" type="string" indexed="true" stored="true" multiValued="true" />
479
- <field name="subject_topic_facet" type="string" indexed="true" stored="true" multiValued="true" />
480
- <field name="subject_era_facet" type="string" indexed="true" stored="true" multiValued="true" />
481
- <field name="subject_geo_facet" type="string" indexed="true" stored="true" multiValued="true" />
482
- <!-- pub_date is used for facet and display so it must be indexed and stored -->
483
- <field name="pub_date" type="string" indexed="true" stored="true" multiValued="true"/>
484
- <!-- pub_date sort uses new trie-based int fields, which are recommended for any int and are displayable, sortable, and range-quer
485
- we use 'tint' for faster range-queries. -->
486
- <field name="pub_date_sort" type="tint" indexed="true" stored="true" multiValued="false"/>
487
-
488
- <!-- format is used for facet, display, and choosing which partial to use for the show view, so it must be stored and indexed -->
489
- <field name="format" type="string" indexed="true" stored="true"/>
490
-
491
-
492
-
493
- <!-- Dynamic field definitions. If a field name is not found, dynamicFields
494
- will be used if the name matches any of the patterns.
495
- RESTRICTION: the glob-like pattern in the name attribute must have
496
- a "*" only at the start or the end.
497
- EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
498
- Longer patterns will be matched first. if equal size patterns
499
- both match, the first appearing in the schema will be used. -->
500
- <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
501
- <dynamicField name="*_s" type="string" indexed="true" stored="true"/>
502
- <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
503
- <dynamicField name="*_t" type="text" indexed="true" stored="true" multiValued="true"/>
504
- <dynamicField name="*_txt" type="text_general" indexed="true" stored="true" multiValued="true"/>
505
- <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
506
- <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
507
- <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
508
-
509
- <!-- Type used to index the lat and lon components for the "location" FieldType -->
510
- <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false"/>
511
-
512
- <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
513
- <dynamicField name="*_p" type="location" indexed="true" stored="true"/>
514
-
515
- <!-- some trie-coded dynamic fields for faster range queries -->
516
- <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
517
- <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
518
- <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
519
- <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
520
- <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
521
-
522
- <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
523
- <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
524
-
525
- <dynamicField name="random_*" type="random" />
526
-
527
- <dynamicField name="*_display" type="string" indexed="false" stored="true" multiValued="true" />
528
- <dynamicField name="*_facet" type="string" indexed="true" stored="false" multiValued="true" />
529
- <dynamicField name="*_sort" type="alphaOnlySort" indexed="true" stored="false" multiValued="false" />
530
- <dynamicField name="*_unstem_search" type="text_general" indexed="true" stored="false" multiValued="true" />
531
- <dynamicField name="*spell" type="textSpell" indexed="true" stored="false" multiValued="true" />
532
- <dynamicField name="*suggest" type="textSuggest" indexed="true" stored="false" multiValued="true" />
533
-
534
- <!-- uncomment the following to ignore any fields that don't already match an existing
535
- field name or dynamic field, rather than reporting them as an error.
536
- alternately, change the type="ignored" to some other type e.g. "text" if you want
537
- unknown fields indexed and/or stored by default -->
538
- <!--dynamicField name="*" type="ignored" multiValued="true" /-->
539
-
540
- </fields>
541
-
542
- <!-- Field to use to determine and enforce document uniqueness.
543
- Unless this field is marked with required="false", it will be a required field
544
- -->
545
- <uniqueKey>id</uniqueKey>
546
-
547
- <!-- field for the QueryParser to use when an explicit fieldname is absent -->
548
- <defaultSearchField>text</defaultSearchField>
549
-
550
- <!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
551
- <solrQueryParser defaultOperator="OR"/>
552
-
553
- <!-- copyField commands copy one field to another at the time a document
554
- is added to the index. It's used either to index the same field differently,
555
- or to add multiple fields to the same field for easier/faster searching. -->
556
- <!-- Copy Fields -->
557
-
558
- <!-- unstemmed fields -->
559
- <copyField source="title_t" dest="title_unstem_search"/>
560
- <copyField source="subtitle_t" dest="subtitle_unstem_search"/>
561
- <copyField source="title_addl_t" dest="title_addl_unstem_search"/>
562
- <copyField source="title_added_entry_t" dest="title_added_entry_unstem_search"/>
563
- <copyField source="title_series_t" dest="title_series_unstem_search"/>
564
- <copyField source="author_t" dest="author_unstem_search"/>
565
- <copyField source="author_addl_t" dest="author_addl_unstem_search"/>
566
- <copyField source="subject_t" dest="subject_unstem_search"/>
567
- <copyField source="subject_addl_t" dest="subject_addl_unstem_search"/>
568
- <copyField source="subject_topic_facet" dest="subject_topic_unstem_search"/>
569
-
570
- <!-- sort fields -->
571
- <copyField source="pub_date" dest="pub_date_sort"/>
572
-
573
-
574
- <!-- spellcheck fields -->
575
- <!-- default spell check; should match fields for default request handler -->
576
- <!-- it won't work with a copy of a copy field -->
577
- <copyField source="*_t" dest="spell"/>
578
- <copyField source="*_facet" dest="spell"/>
579
- <!-- title spell check; should match fields for title request handler -->
580
- <copyField source="title_t" dest="title_spell"/>
581
- <copyField source="subtitle_t" dest="title_spell"/>
582
- <copyField source="addl_titles_t" dest="title_spell"/>
583
- <copyField source="title_added_entry_t" dest="title_spell"/>
584
- <copyField source="title_series_t" dest="title_spell"/>
585
- <!-- author spell check; should match fields for author request handler -->
586
- <copyField source="author_t" dest="author_spell"/>
587
- <copyField source="author_addl_t" dest="author_spell"/>
588
- <!-- subject spell check; should match fields for subject request handler -->
589
- <copyField source="subject_topic_facet" dest="subject_spell"/>
590
- <copyField source="subject_t" dest="subject_spell"/>
591
- <copyField source="subject_addl_t" dest="subject_spell"/>
592
-
593
- <!-- OpenSearch query field should match request handler search fields -->
594
- <copyField source="title_t" dest="opensearch_display"/>
595
- <copyField source="subtitle_t" dest="opensearch_display"/>
596
- <copyField source="addl_titles_t" dest="opensearch_display"/>
597
- <copyField source="title_added_entry_t" dest="opensearch_display"/>
598
- <copyField source="title_series_t" dest="opensearch_display"/>
599
- <copyField source="author_t" dest="opensearch_display"/>
600
- <copyField source="author_addl_t" dest="opensearch_display"/>
601
- <copyField source="subject_topic_facet" dest="opensearch_display"/>
602
- <copyField source="subject_t" dest="opensearch_display"/>
603
- <copyField source="subject_addl_t" dest="opensearch_display"/>
604
-
605
- <!-- for suggestions -->
606
- <copyField source="*_t" dest="suggest"/>
607
- <copyField source="*_facet" dest="suggest"/>
608
-
609
- <!-- Above, multiple source fields are copied to the [text] field.
610
- Another way to map multiple source fields to the same
611
- destination field is to use the dynamic field syntax.
612
- copyField also supports a maxChars to copy setting. -->
613
-
614
- <!-- <copyField source="*_t" dest="text" maxChars="3000"/> -->
615
-
616
- <!-- copy name to alphaNameSort, a field designed for sorting by name -->
617
- <!-- <copyField source="name" dest="alphaNameSort"/> -->
618
-
619
-
620
- <!-- Similarity is the scoring routine for each document vs. a query.
621
- A custom similarity may be specified here, but the default is fine
622
- for most applications. -->
623
- <!-- <similarity class="org.apache.lucene.search.DefaultSimilarity"/> -->
624
- <!-- ... OR ...
625
- Specify a SimilarityFactory class name implementation
626
- allowing parameters to be used.
627
- -->
628
- <!--
629
- <similarity class="com.example.solr.CustomSimilarityFactory">
630
- <str name="paramkey">param value</str>
631
- </similarity>
632
- -->
633
-
386
+ </types>
634
387
 
635
388
  </schema>