active-fedora 9.8.0 → 9.8.1

Sign up to get free protection for your applications and to get access to all the features.
Files changed (23) hide show
  1. checksums.yaml +4 -4
  2. data/lib/active_fedora/file.rb +46 -32
  3. data/lib/active_fedora/version.rb +1 -1
  4. data/lib/generators/active_fedora/config/solr/solr_generator.rb +1 -1
  5. data/lib/generators/active_fedora/config/solr/templates/solr/config/_rest_managed.json +3 -0
  6. data/lib/generators/active_fedora/config/solr/templates/solr/config/admin-extra.html +31 -0
  7. data/lib/generators/active_fedora/config/solr/templates/{solr_conf/solr.xml → solr/config/elevate.xml} +36 -35
  8. data/lib/generators/active_fedora/config/solr/templates/solr/config/mapping-ISOLatin1Accent.txt +246 -0
  9. data/lib/generators/active_fedora/config/solr/templates/solr/config/protwords.txt +21 -0
  10. data/lib/generators/active_fedora/config/solr/templates/{solr_conf/conf → solr/config}/schema.xml +217 -123
  11. data/lib/generators/active_fedora/config/solr/templates/solr/config/scripts.conf +24 -0
  12. data/lib/generators/active_fedora/config/solr/templates/solr/config/solrconfig.xml +419 -0
  13. data/lib/generators/active_fedora/config/solr/templates/solr/config/spellings.txt +2 -0
  14. data/lib/generators/active_fedora/config/solr/templates/solr/config/stopwords.txt +58 -0
  15. data/lib/generators/active_fedora/config/solr/templates/solr/config/stopwords_en.txt +58 -0
  16. data/lib/generators/active_fedora/config/solr/templates/solr/config/synonyms.txt +31 -0
  17. data/lib/generators/active_fedora/config/solr/templates/solr/config/xslt/example.xsl +132 -0
  18. data/lib/generators/active_fedora/config/solr/templates/solr/config/xslt/example_atom.xsl +67 -0
  19. data/lib/generators/active_fedora/config/solr/templates/solr/config/xslt/example_rss.xsl +66 -0
  20. data/lib/generators/active_fedora/config/solr/templates/solr/config/xslt/luke.xsl +337 -0
  21. data/spec/unit/file_spec.rb +105 -0
  22. metadata +17 -4
  23. data/lib/generators/active_fedora/config/solr/templates/solr_conf/conf/solrconfig.xml +0 -218
@@ -0,0 +1,21 @@
1
+ # The ASF licenses this file to You under the Apache License, Version 2.0
2
+ # (the "License"); you may not use this file except in compliance with
3
+ # the License. You may obtain a copy of the License at
4
+ #
5
+ # http://www.apache.org/licenses/LICENSE-2.0
6
+ #
7
+ # Unless required by applicable law or agreed to in writing, software
8
+ # distributed under the License is distributed on an "AS IS" BASIS,
9
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
10
+ # See the License for the specific language governing permissions and
11
+ # limitations under the License.
12
+
13
+ #-----------------------------------------------------------------------
14
+ # Use a protected word file to protect against the stemmer reducing two
15
+ # unrelated words to the same base word.
16
+
17
+ # Some non-words that normally won't be encountered,
18
+ # just to test that they won't be stemmed.
19
+ dontstems
20
+ zwhacky
21
+
@@ -1,11 +1,181 @@
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 -->
6
-
7
- <uniqueKey>id</uniqueKey>
8
-
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="Hydra 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
+ -->
59
+
60
+ <types>
61
+ <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
62
+ <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
63
+ <fieldType name="rand" class="solr.RandomSortField" omitNorms="true"/>
64
+
65
+ <!-- Default numeric field types. -->
66
+ <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
67
+ <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
68
+ <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
69
+ <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
70
+
71
+ <!-- trie numeric field types for faster range queries -->
72
+ <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
73
+ <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
74
+ <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
75
+ <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
76
+
77
+ <!-- The format for this date field is of the form 1995-12-31T23:59:59Z
78
+ Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
79
+ -->
80
+ <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
81
+ <!-- A Trie based date field for faster date range queries and date faceting. -->
82
+ <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
83
+
84
+
85
+ <!-- This point type indexes the coordinates as separate fields (subFields)
86
+ If subFieldType is defined, it references a type, and a dynamic field
87
+ definition is created matching *___<typename>. Alternately, if
88
+ subFieldSuffix is defined, that is used to create the subFields.
89
+ Example: if subFieldType="double", then the coordinates would be
90
+ indexed in fields myloc_0___double,myloc_1___double.
91
+ Example: if subFieldSuffix="_d" then the coordinates would be indexed
92
+ in fields myloc_0_d,myloc_1_d
93
+ The subFields are an implementation detail of the fieldType, and end
94
+ users normally should not need to know about them.
95
+ -->
96
+ <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
97
+
98
+ <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
99
+ <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
100
+
101
+ <!-- An alternative geospatial field type new to Solr 4. It supports multiValued and polygon shapes.
102
+ For more information about this and other Spatial fields new to Solr 4, see:
103
+ http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
104
+ -->
105
+ <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
106
+ geo="true" distErrPct="0.025" maxDistErr="0.000009" units="degrees" />
107
+
108
+ <fieldType name="text" class="solr.TextField" omitNorms="false">
109
+ <analyzer>
110
+ <tokenizer class="solr.ICUTokenizerFactory"/>
111
+ <filter class="solr.ICUFoldingFilterFactory"/> <!-- NFKC, case folding, diacritics removed -->
112
+ <filter class="solr.TrimFilterFactory"/>
113
+ </analyzer>
114
+ </fieldType>
115
+
116
+ <!-- A text field that only splits on whitespace for exact matching of words -->
117
+ <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
118
+ <analyzer>
119
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
120
+ <filter class="solr.TrimFilterFactory"/>
121
+ </analyzer>
122
+ </fieldType>
123
+
124
+ <!-- single token analyzed text, for sorting. Punctuation is significant. -->
125
+ <fieldtype name="alphaSort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
126
+ <analyzer>
127
+ <tokenizer class="solr.KeywordTokenizerFactory" />
128
+ <filter class="solr.ICUFoldingFilterFactory"/>
129
+ <filter class="solr.TrimFilterFactory" />
130
+ </analyzer>
131
+ </fieldtype>
132
+
133
+ <!-- A text field with defaults appropriate for English -->
134
+ <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
135
+ <analyzer>
136
+ <tokenizer class="solr.ICUTokenizerFactory"/>
137
+ <filter class="solr.ICUFoldingFilterFactory"/> <!-- NFKC, case folding, diacritics removed -->
138
+ <filter class="solr.EnglishPossessiveFilterFactory"/>
139
+ <!-- EnglishMinimalStemFilterFactory is less aggressive than PorterStemFilterFactory: -->
140
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>
141
+ <!--
142
+ <filter class="solr.PorterStemFilterFactory"/>
143
+ -->
144
+ <filter class="solr.TrimFilterFactory"/>
145
+ </analyzer>
146
+ </fieldType>
147
+
148
+ <!-- queries for paths match documents at that path, or in descendent paths -->
149
+ <fieldType name="descendent_path" class="solr.TextField">
150
+ <analyzer type="index">
151
+ <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
152
+ </analyzer>
153
+ <analyzer type="query">
154
+ <tokenizer class="solr.KeywordTokenizerFactory" />
155
+ </analyzer>
156
+ </fieldType>
157
+
158
+ <!-- queries for paths match documents at that path, or in ancestor paths -->
159
+ <fieldType name="ancestor_path" class="solr.TextField">
160
+ <analyzer type="index">
161
+ <tokenizer class="solr.KeywordTokenizerFactory" />
162
+ </analyzer>
163
+ <analyzer type="query">
164
+ <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
165
+ </analyzer>
166
+ </fieldType>
167
+
168
+ <fieldType class="solr.TextField" name="textSuggest" positionIncrementGap="100">
169
+ <analyzer>
170
+ <tokenizer class="solr.KeywordTokenizerFactory"/>
171
+ <filter class="solr.StandardFilterFactory"/>
172
+ <filter class="solr.LowerCaseFilterFactory"/>
173
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
174
+ </analyzer>
175
+ </fieldType>
176
+ </types>
177
+
178
+
9
179
  <fields>
10
180
  <!-- If you remove this field, you must _also_ disable the update log in solrconfig.xml
11
181
  or Solr won't start. _version_ and update log are required for SolrCloud
@@ -151,128 +321,52 @@
151
321
  <dynamicField name="*_llsi" type="location" stored="true" indexed="true" multiValued="false"/>
152
322
  <dynamicField name="*_llsim" type="location" stored="true" indexed="true" multiValued="true"/>
153
323
 
324
+ <dynamicField name="*suggest" type="textSuggest" indexed="true" stored="false" multiValued="true" />
325
+
154
326
  <!-- you must define copyField source and dest fields explicity or schemaBrowser doesn't work -->
155
327
  <field name="all_text_timv" type="text" stored="false" indexed="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
156
328
 
157
329
 
158
330
  </fields>
159
331
 
332
+ <!-- Field to use to determine and enforce document uniqueness.
333
+ Unless this field is marked with required="false", it will be a required field
334
+ -->
335
+ <uniqueKey>id</uniqueKey>
160
336
 
161
- <!-- Above, multiple source fields are copied to the [text] field.
162
- Another way to map multiple source fields to the same
163
- destination field is to use the dynamic field syntax.
164
- copyField also supports a maxChars to copy setting. -->
337
+ <!-- field for the QueryParser to use when an explicit fieldname is absent -->
338
+ <!-- <defaultSearchField>text</defaultSearchField> -->
165
339
 
166
- <!-- <copyField source="*_tesim" dest="all_text_timv" maxChars="3000"/> -->
340
+ <!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
341
+ <solrQueryParser defaultOperator="OR"/>
342
+
343
+ <!-- copyField commands copy one field to another at the time a document
344
+ is added to the index. It's used either to index the same field differently,
345
+ or to add multiple fields to the same field for easier/faster searching. -->
346
+ <!-- Copy Fields -->
347
+
348
+ <!-- Above, multiple source fields are copied to the [text] field.
349
+ Another way to map multiple source fields to the same
350
+ destination field is to use the dynamic field syntax.
351
+ copyField also supports a maxChars to copy setting. -->
352
+
353
+ <!-- <copyField source="*_tesim" dest="all_text_timv" maxChars="3000"/> -->
354
+ <!-- for suggestions -->
355
+ <copyField source="*_tesim" dest="suggest"/>
356
+ <copyField source="*_ssim" dest="suggest"/>
357
+
358
+ <!-- Similarity is the scoring routine for each document vs. a query.
359
+ A custom similarity may be specified here, but the default is fine
360
+ for most applications. -->
361
+ <!-- <similarity class="org.apache.lucene.search.DefaultSimilarity"/> -->
362
+ <!-- ... OR ...
363
+ Specify a SimilarityFactory class name implementation
364
+ allowing parameters to be used.
365
+ -->
366
+ <!--
367
+ <similarity class="com.example.solr.CustomSimilarityFactory">
368
+ <str name="paramkey">param value</str>
369
+ </similarity>
370
+ -->
167
371
 
168
- <types>
169
- <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
170
- <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
171
- <fieldType name="rand" class="solr.RandomSortField" omitNorms="true"/>
172
-
173
- <!-- Default numeric field types. -->
174
- <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
175
- <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
176
- <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
177
- <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
178
-
179
- <!-- trie numeric field types for faster range queries -->
180
- <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
181
- <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
182
- <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
183
- <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
184
-
185
- <!-- The format for this date field is of the form 1995-12-31T23:59:59Z
186
- Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
187
- -->
188
- <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
189
- <!-- A Trie based date field for faster date range queries and date faceting. -->
190
- <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
191
-
192
-
193
- <!-- This point type indexes the coordinates as separate fields (subFields)
194
- If subFieldType is defined, it references a type, and a dynamic field
195
- definition is created matching *___<typename>. Alternately, if
196
- subFieldSuffix is defined, that is used to create the subFields.
197
- Example: if subFieldType="double", then the coordinates would be
198
- indexed in fields myloc_0___double,myloc_1___double.
199
- Example: if subFieldSuffix="_d" then the coordinates would be indexed
200
- in fields myloc_0_d,myloc_1_d
201
- The subFields are an implementation detail of the fieldType, and end
202
- users normally should not need to know about them.
203
- -->
204
- <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
205
-
206
- <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
207
- <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
208
-
209
- <!-- An alternative geospatial field type new to Solr 4. It supports multiValued and polygon shapes.
210
- For more information about this and other Spatial fields new to Solr 4, see:
211
- http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
212
- -->
213
- <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
214
- geo="true" distErrPct="0.025" maxDistErr="0.000009" units="degrees" />
215
-
216
- <fieldType name="text" class="solr.TextField" omitNorms="false">
217
- <analyzer>
218
- <tokenizer class="solr.ICUTokenizerFactory"/>
219
- <filter class="solr.ICUFoldingFilterFactory"/> <!-- NFKC, case folding, diacritics removed -->
220
- <filter class="solr.TrimFilterFactory"/>
221
- </analyzer>
222
- </fieldType>
223
-
224
- <!-- A text field that only splits on whitespace for exact matching of words -->
225
- <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
226
- <analyzer>
227
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
228
- <filter class="solr.TrimFilterFactory"/>
229
- </analyzer>
230
- </fieldType>
231
-
232
- <!-- single token analyzed text, for sorting. Punctuation is significant. -->
233
- <fieldtype name="alphaSort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
234
- <analyzer>
235
- <tokenizer class="solr.KeywordTokenizerFactory" />
236
- <filter class="solr.ICUFoldingFilterFactory"/>
237
- <filter class="solr.TrimFilterFactory" />
238
- </analyzer>
239
- </fieldtype>
240
-
241
- <!-- A text field with defaults appropriate for English -->
242
- <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
243
- <analyzer>
244
- <tokenizer class="solr.ICUTokenizerFactory"/>
245
- <filter class="solr.ICUFoldingFilterFactory"/> <!-- NFKC, case folding, diacritics removed -->
246
- <filter class="solr.EnglishPossessiveFilterFactory"/>
247
- <!-- EnglishMinimalStemFilterFactory is less aggressive than PorterStemFilterFactory: -->
248
- <filter class="solr.EnglishMinimalStemFilterFactory"/>
249
- <!--
250
- <filter class="solr.PorterStemFilterFactory"/>
251
- -->
252
- <filter class="solr.TrimFilterFactory"/>
253
- </analyzer>
254
- </fieldType>
255
-
256
- <!-- queries for paths match documents at that path, or in descendent paths -->
257
- <fieldType name="descendent_path" class="solr.TextField">
258
- <analyzer type="index">
259
- <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
260
- </analyzer>
261
- <analyzer type="query">
262
- <tokenizer class="solr.KeywordTokenizerFactory" />
263
- </analyzer>
264
- </fieldType>
265
-
266
- <!-- queries for paths match documents at that path, or in ancestor paths -->
267
- <fieldType name="ancestor_path" class="solr.TextField">
268
- <analyzer type="index">
269
- <tokenizer class="solr.KeywordTokenizerFactory" />
270
- </analyzer>
271
- <analyzer type="query">
272
- <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
273
- </analyzer>
274
- </fieldType>
275
-
276
- </types>
277
-
278
372
  </schema>
@@ -0,0 +1,24 @@
1
+ # Licensed to the Apache Software Foundation (ASF) under one or more
2
+ # contributor license agreements. See the NOTICE file distributed with
3
+ # this work for additional information regarding copyright ownership.
4
+ # The ASF licenses this file to You under the Apache License, Version 2.0
5
+ # (the "License"); you may not use this file except in compliance with
6
+ # the License. You may obtain a copy of the License at
7
+ #
8
+ # http://www.apache.org/licenses/LICENSE-2.0
9
+ #
10
+ # Unless required by applicable law or agreed to in writing, software
11
+ # distributed under the License is distributed on an "AS IS" BASIS,
12
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13
+ # See the License for the specific language governing permissions and
14
+ # limitations under the License.
15
+
16
+ user=
17
+ solr_hostname=localhost
18
+ solr_port=8983
19
+ rsyncd_port=18983
20
+ data_dir=
21
+ webapp_name=solr
22
+ master_host=
23
+ master_data_dir=
24
+ master_status_dir=
@@ -0,0 +1,419 @@
1
+ <?xml version="1.0" encoding="UTF-8" ?>
2
+ <!--
3
+ Licensed to the Apache Software Foundation (ASF) under one or more
4
+ contributor license agreements. See the NOTICE file distributed with
5
+ this work for additional information regarding copyright ownership.
6
+ The ASF licenses this file to You under the Apache License, Version 2.0
7
+ (the "License"); you may not use this file except in compliance with
8
+ the License. You may obtain a copy of the License at
9
+
10
+ http://www.apache.org/licenses/LICENSE-2.0
11
+
12
+ Unless required by applicable law or agreed to in writing, software
13
+ distributed under the License is distributed on an "AS IS" BASIS,
14
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15
+ See the License for the specific language governing permissions and
16
+ limitations under the License.
17
+ -->
18
+
19
+ <!--
20
+ This is a stripped down config file used for a simple example...
21
+ It is *not* a good example to work from.
22
+ -->
23
+ <config>
24
+
25
+ <!-- Controls what version of Lucene various components of Solr
26
+ adhere to. Generally, you want to use the latest version to
27
+ get all bug fixes and improvements. It is highly recommended
28
+ that you fully re-index after changing this setting as it can
29
+ affect both how text is indexed and queried.
30
+ -->
31
+ <luceneMatchVersion>5.0.0</luceneMatchVersion>
32
+
33
+ <lib dir="${solr.install.dir:../../../..}/contrib/analysis-extras/lib" />
34
+ <lib dir="${solr.install.dir:../../../..}/contrib/analysis-extras/lucene-libs" />
35
+
36
+ <directoryFactory name="DirectoryFactory"
37
+ class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}">
38
+ </directoryFactory>
39
+
40
+ <codecFactory class="solr.SchemaCodecFactory"/>
41
+
42
+ <schemaFactory class="ClassicIndexSchemaFactory"/>
43
+
44
+
45
+ <dataDir>${solr.blacklight-core.data.dir:}</dataDir>
46
+
47
+ <requestDispatcher handleSelect="true" >
48
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="2048" />
49
+ </requestDispatcher>
50
+
51
+ <requestHandler name="/analysis/field" startup="lazy" class="solr.FieldAnalysisRequestHandler" />
52
+
53
+ <!-- config for the admin interface -->
54
+ <admin>
55
+ <defaultQuery>*:*</defaultQuery>
56
+ </admin>
57
+
58
+ <!-- SearchHandler
59
+
60
+ http://wiki.apache.org/solr/SearchHandler
61
+
62
+ For processing Search Queries, the primary Request Handler
63
+ provided with Solr is "SearchHandler" It delegates to a sequent
64
+ of SearchComponents (see below) and supports distributed
65
+ queries across multiple shards
66
+ -->
67
+ <requestHandler name="search" class="solr.SearchHandler" default="true">
68
+ <!-- default values for query parameters can be specified, these
69
+ will be overridden by parameters in the request
70
+ -->
71
+ <lst name="defaults">
72
+ <str name="defType">dismax</str>
73
+ <str name="echoParams">explicit</str>
74
+ <int name="rows">10</int>
75
+
76
+ <str name="q.alt">*:*</str>
77
+ <str name="mm">2&lt;-1 5&lt;-2 6&lt;90%</str>
78
+
79
+ <!-- this qf and pf are used by default, if not otherwise specified by
80
+ client. The default blacklight_config will use these for the
81
+ "keywords" search. See the author_qf/author_pf, title_qf, etc
82
+ below, which the default blacklight_config will specify for
83
+ those searches. You may also be interested in:
84
+ http://wiki.apache.org/solr/LocalParams
85
+ -->
86
+
87
+ <str name="qf">
88
+ title_unstem_search^100000
89
+ subtitle_unstem_search^50000
90
+ title_t^25000
91
+ subtitle_t^10000
92
+ title_addl_unstem_search^5000
93
+ title_addl_t^2500
94
+ title_added_entry_unstem_search^1500
95
+ title_added_entry_t^1250
96
+ subject_topic_unstem_search^1000
97
+ subject_unstem_search^750
98
+ subject_topic_facet^625
99
+ subject_t^500
100
+ author_unstem_search^250
101
+ author_addl_unstem_search^250
102
+ author_t^100
103
+ author_addl_t^50
104
+ subject_addl_unstem_search^250
105
+ subject_addl_t^50
106
+ title_series_unstem_search^25
107
+ title_series_t^10
108
+ isbn_t
109
+ text
110
+ </str>
111
+ <str name="pf">
112
+ title_unstem_search^1000000
113
+ subtitle_unstem_search^500000
114
+ title_t^250000
115
+ subtitle_t^100000
116
+ title_addl_unstem_search^50000
117
+ title_addl_t^25000
118
+ title_added_entry_unstem_search^15000
119
+ title_added_entry_t^12500
120
+ subject_topic_unstem_search^10000
121
+ subject_unstem_search^7500
122
+ subject_topic_facet^6250
123
+ subject_t^5000
124
+ author_unstem_search^2500
125
+ author_addl_unstem_search^2500
126
+ author_t^1000
127
+ author_addl_t^500
128
+ subject_addl_unstem_search^2500
129
+ subject_addl_t^500
130
+ title_series_unstem_search^250
131
+ title_series_t^100
132
+ text^10
133
+ </str>
134
+ <str name="author_qf">
135
+ author_unstem_search^200
136
+ author_addl_unstem_search^50
137
+ author_t^20
138
+ author_addl_t
139
+ </str>
140
+ <str name="author_pf">
141
+ author_unstem_search^2000
142
+ author_addl_unstem_search^500
143
+ author_t^200
144
+ author_addl_t^10
145
+ </str>
146
+ <str name="title_qf">
147
+ title_unstem_search^50000
148
+ subtitle_unstem_search^25000
149
+ title_addl_unstem_search^10000
150
+ title_t^5000
151
+ subtitle_t^2500
152
+ title_addl_t^100
153
+ title_added_entry_unstem_search^50
154
+ title_added_entry_t^10
155
+ title_series_unstem_search^5
156
+ title_series_t
157
+ </str>
158
+ <str name="title_pf">
159
+ title_unstem_search^500000
160
+ subtitle_unstem_search^250000
161
+ title_addl_unstem_search^100000
162
+ title_t^50000
163
+ subtitle_t^25000
164
+ title_addl_t^1000
165
+ title_added_entry_unstem_search^500
166
+ title_added_entry_t^100
167
+ title_series_t^50
168
+ title_series_unstem_search^10
169
+ </str>
170
+ <str name="subject_qf">
171
+ subject_topic_unstem_search^200
172
+ subject_unstem_search^125
173
+ subject_topic_facet^100
174
+ subject_t^50
175
+ subject_addl_unstem_search^10
176
+ subject_addl_t
177
+ </str>
178
+ <str name="subject_pf">
179
+ subject_topic_unstem_search^2000
180
+ subject_unstem_search^1250
181
+ subject_t^1000
182
+ subject_topic_facet^500
183
+ subject_addl_unstem_search^100
184
+ subject_addl_t^10
185
+ </str>
186
+
187
+ <int name="ps">3</int>
188
+ <float name="tie">0.01</float>
189
+
190
+ <!-- NOT using marc_display because it is large and will slow things down for search results -->
191
+ <str name="fl">
192
+ id,
193
+ score,
194
+ author_display,
195
+ author_vern_display,
196
+ format,
197
+ isbn_t,
198
+ language_facet,
199
+ lc_callnum_display,
200
+ material_type_display,
201
+ published_display,
202
+ published_vern_display,
203
+ pub_date,
204
+ title_display,
205
+ title_vern_display,
206
+ subject_topic_facet,
207
+ subject_geo_facet,
208
+ subject_era_facet,
209
+ subtitle_display,
210
+ subtitle_vern_display,
211
+ url_fulltext_display,
212
+ url_suppl_display,
213
+ </str>
214
+
215
+ <str name="facet">true</str>
216
+ <str name="facet.mincount">1</str>
217
+ <str name="facet.limit">10</str>
218
+ <str name="facet.field">format</str>
219
+ <str name="facet.field">lc_1letter_facet</str>
220
+ <str name="facet.field">lc_alpha_facet</str>
221
+ <str name="facet.field">lc_b4cutter_facet</str>
222
+ <str name="facet.field">language_facet</str>
223
+ <str name="facet.field">pub_date</str>
224
+ <str name="facet.field">subject_era_facet</str>
225
+ <str name="facet.field">subject_geo_facet</str>
226
+ <str name="facet.field">subject_topic_facet</str>
227
+
228
+ <str name="spellcheck">true</str>
229
+ <str name="spellcheck.dictionary">default</str>
230
+ <str name="spellcheck.onlyMorePopular">true</str>
231
+ <str name="spellcheck.extendedResults">true</str>
232
+ <str name="spellcheck.collate">false</str>
233
+ <str name="spellcheck.count">5</str>
234
+
235
+ </lst>
236
+ <!-- In addition to defaults, "appends" params can be specified
237
+ to identify values which should be appended to the list of
238
+ multi-val params from the query (or the existing "defaults").
239
+ -->
240
+ <!-- In this example, the param "fq=instock:true" would be appended to
241
+ any query time fq params the user may specify, as a mechanism for
242
+ partitioning the index, independent of any user selected filtering
243
+ that may also be desired (perhaps as a result of faceted searching).
244
+
245
+ NOTE: there is *absolutely* nothing a client can do to prevent these
246
+ "appends" values from being used, so don't use this mechanism
247
+ unless you are sure you always want it.
248
+ -->
249
+ <!--
250
+ <lst name="appends">
251
+ <str name="fq">inStock:true</str>
252
+ </lst>
253
+ -->
254
+ <!-- "invariants" are a way of letting the Solr maintainer lock down
255
+ the options available to Solr clients. Any params values
256
+ specified here are used regardless of what values may be specified
257
+ in either the query, the "defaults", or the "appends" params.
258
+
259
+ In this example, the facet.field and facet.query params would
260
+ be fixed, limiting the facets clients can use. Faceting is
261
+ not turned on by default - but if the client does specify
262
+ facet=true in the request, these are the only facets they
263
+ will be able to see counts for; regardless of what other
264
+ facet.field or facet.query params they may specify.
265
+
266
+ NOTE: there is *absolutely* nothing a client can do to prevent these
267
+ "invariants" values from being used, so don't use this mechanism
268
+ unless you are sure you always want it.
269
+ -->
270
+ <!--
271
+ <lst name="invariants">
272
+ <str name="facet.field">cat</str>
273
+ <str name="facet.field">manu_exact</str>
274
+ <str name="facet.query">price:[* TO 500]</str>
275
+ <str name="facet.query">price:[500 TO *]</str>
276
+ </lst>
277
+ -->
278
+ <!-- If the default list of SearchComponents is not desired, that
279
+ list can either be overridden completely, or components can be
280
+ prepended or appended to the default list. (see below)
281
+ -->
282
+ <!--
283
+ <arr name="components">
284
+ <str>nameOfCustomComponent1</str>
285
+ <str>nameOfCustomComponent2</str>
286
+ </arr>
287
+ -->
288
+ <arr name="last-components">
289
+ <str>spellcheck</str>
290
+ </arr>
291
+
292
+ </requestHandler>
293
+
294
+ <requestHandler name="standard" class="solr.SearchHandler">
295
+ <lst name="defaults">
296
+ <str name="echoParams">explicit</str>
297
+ <str name="defType">lucene</str>
298
+ </lst>
299
+ </requestHandler>
300
+
301
+ <!-- for requests to get a single document; use id=666 instead of q=id:666 -->
302
+ <requestHandler name="document" class="solr.SearchHandler" >
303
+ <lst name="defaults">
304
+ <str name="echoParams">all</str>
305
+ <str name="fl">*</str>
306
+ <str name="rows">1</str>
307
+ <str name="q">{!term f=id v=$id}</str> <!-- use id=666 instead of q=id:666 -->
308
+ </lst>
309
+ </requestHandler>
310
+
311
+ <!-- Spell Check
312
+
313
+ The spell check component can return a list of alternative spelling
314
+ suggestions.
315
+
316
+ http://wiki.apache.org/solr/SpellCheckComponent
317
+ -->
318
+ <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
319
+
320
+ <str name="queryAnalyzerFieldType">textSpell</str>
321
+
322
+ <!-- Multiple "Spell Checkers" can be declared and used by this
323
+ component
324
+ -->
325
+
326
+ <!-- a spellchecker built from a field of the main index, and
327
+ written to disk
328
+ -->
329
+ <lst name="spellchecker">
330
+ <str name="name">default</str>
331
+ <str name="field">spell</str>
332
+ <str name="spellcheckIndexDir">./spell</str>
333
+ <str name="buildOnOptimize">true</str>
334
+ </lst>
335
+ <lst name="spellchecker">
336
+ <str name="name">author</str>
337
+ <str name="field">author_spell</str>
338
+ <str name="spellcheckIndexDir">./spell_author</str>
339
+ <str name="accuracy">0.7</str>
340
+ <str name="buildOnOptimize">true</str>
341
+ </lst>
342
+ <lst name="spellchecker">
343
+ <str name="name">subject</str>
344
+ <str name="field">subject_spell</str>
345
+ <str name="spellcheckIndexDir">./spell_subject</str>
346
+ <str name="accuracy">0.7</str>
347
+ <str name="buildOnOptimize">true</str>
348
+ </lst>
349
+ <lst name="spellchecker">
350
+ <str name="name">title</str>
351
+ <str name="field">title_spell</str>
352
+ <str name="spellcheckIndexDir">./spell_title</str>
353
+ <str name="accuracy">0.7</str>
354
+ <str name="buildOnOptimize">true</str>
355
+ </lst>
356
+
357
+ <!-- a spellchecker that uses a different distance measure -->
358
+ <!--
359
+ <lst name="spellchecker">
360
+ <str name="name">jarowinkler</str>
361
+ <str name="field">spell</str>
362
+ <str name="distanceMeasure">
363
+ org.apache.lucene.search.spell.JaroWinklerDistance
364
+ </str>
365
+ <str name="spellcheckIndexDir">spellcheckerJaro</str>
366
+ </lst>
367
+ -->
368
+
369
+ <!-- a spellchecker that use an alternate comparator
370
+
371
+ comparatorClass be one of:
372
+ 1. score (default)
373
+ 2. freq (Frequency first, then score)
374
+ 3. A fully qualified class name
375
+ -->
376
+ <!--
377
+ <lst name="spellchecker">
378
+ <str name="name">freq</str>
379
+ <str name="field">lowerfilt</str>
380
+ <str name="spellcheckIndexDir">spellcheckerFreq</str>
381
+ <str name="comparatorClass">freq</str>
382
+ <str name="buildOnCommit">true</str>
383
+ -->
384
+
385
+ <!-- A spellchecker that reads the list of words from a file -->
386
+ <!--
387
+ <lst name="spellchecker">
388
+ <str name="classname">solr.FileBasedSpellChecker</str>
389
+ <str name="name">file</str>
390
+ <str name="sourceLocation">spellings.txt</str>
391
+ <str name="characterEncoding">UTF-8</str>
392
+ <str name="spellcheckIndexDir">spellcheckerFile</str>
393
+ </lst>
394
+ -->
395
+ </searchComponent>
396
+
397
+ <searchComponent name="suggest" class="solr.SuggestComponent">
398
+ <lst name="suggester">
399
+ <str name="name">mySuggester</str>
400
+ <str name="lookupImpl">FuzzyLookupFactory</str>
401
+ <str name="suggestAnalyzerFieldType">textSuggest</str>
402
+ <str name="buildOnCommit">true</str>
403
+ <str name="field">suggest</str>
404
+ </lst>
405
+ </searchComponent>
406
+
407
+ <requestHandler name="/suggest" class="solr.SearchHandler" startup="lazy">
408
+ <lst name="defaults">
409
+ <str name="suggest">true</str>
410
+ <str name="suggest.count">5</str>
411
+ <str name="suggest.dictionary">mySuggester</str>
412
+ </lst>
413
+ <arr name="components">
414
+ <str>suggest</str>
415
+ </arr>
416
+ </requestHandler>
417
+
418
+ </config>
419
+