common_repository_model 0.0.9 → 0.1.0

This diff has not been reviewed by any users.
Sign up to get free protection for your applications and to get access to all the features.
Files changed (12) hide show
  1. data/common_repository_model.gemspec +4 -4
  2. data/config/schema.xml +125 -0
  3. data/config/solrconfig.xml +1882 -1858
  4. data/lib/common_repository_model.rb +1 -0
  5. data/lib/common_repository_model/exceptions.rb +10 -0
  6. data/lib/common_repository_model/persistence_base.rb +9 -11
  7. data/lib/common_repository_model/version.rb +1 -1
  8. data/lib/generators/common_repository_model/collection/collection_generator.rb +1 -1
  9. data/lib/tasks/common_repository_model.tasks +15 -0
  10. data/spec/common_respository_model/data_spec.rb +13 -12
  11. data/spec/common_respository_model/persistence_base_spec.rb +13 -0
  12. metadata +18 -16
data/common_repository_model.gemspec CHANGED
@@ -25,8 +25,8 @@ Gem::Specification.new do |gem|
25
25
  gem.add_dependency "activemodel", "~>3.2"
26
26
  gem.add_dependency "builder", "~>3.0"
27
27
  gem.add_dependency "active_model_serializers"
28
- gem.add_runtime_dependency "minitest"
29
- gem.add_runtime_dependency "minitest-matchers"
30
- gem.add_runtime_dependency "active-fedora", "5.0.0.rc3"
31
- gem.add_runtime_dependency "factory_girl"
28
+ gem.add_dependency "active-fedora", "5.2.0"
29
+ gem.add_development_dependency "minitest"
30
+ gem.add_development_dependency "minitest-matchers"
31
+ gem.add_development_dependency "factory_girl"
32
32
  end
data/config/schema.xml ADDED
@@ -0,0 +1,125 @@
1
+ <?xml version="1.0" encoding="UTF-8" ?>
2
+ <!--
3
+ IMPORTANT
4
+ This copy of the solr schema is only used in the context of testing hydra-head. If you want to make changes available to individual hydra heads, you must apply them to the template in lib/generators/hydra/templates/solr_config
5
+ -->
6
+ <schema name="Hydra" version="1.1">
7
+ <!-- For complete comments from the Solr project example schema.xml:
8
+ http://svn.apache.org/viewvc/lucene/dev/trunk/solr/example/solr/conf/schema.xml?view=markup
9
+ See also:
10
+ http://wiki.apache.org/solr/SchemaXml
11
+ -->
12
+ <types>
13
+ <fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
14
+ <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
15
+ <fieldType name="integer" class="solr.IntField" omitNorms="true"/>
16
+ <fieldType name="long" class="solr.LongField" omitNorms="true"/>
17
+ <fieldType name="float" class="solr.FloatField" omitNorms="true"/>
18
+ <fieldType name="double" class="solr.DoubleField" omitNorms="true"/>
19
+ <fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/>
20
+ <fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/>
21
+ <fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/>
22
+ <fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/>
23
+ <fieldType name="date" class="solr.DateField" sortMissingLast="true" omitNorms="true"/>
24
+ <fieldType name="random" class="solr.RandomSortField" indexed="true" />
25
+
26
+ <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
27
+ <analyzer>
28
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
29
+ </analyzer>
30
+ </fieldType>
31
+
32
+ <fieldType name="text" class="solr.TextField" positionIncrementGap="100">
33
+ <analyzer type="index">
34
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
35
+ <filter class="solr.StopFilterFactory"
36
+ ignoreCase="true"
37
+ words="stopwords.txt"
38
+ enablePositionIncrements="true"
39
+ />
40
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
41
+ <filter class="solr.LowerCaseFilterFactory"/>
42
+ <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
43
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
44
+ </analyzer>
45
+ <analyzer type="query">
46
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
47
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
48
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
49
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
50
+ <filter class="solr.LowerCaseFilterFactory"/>
51
+ <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
52
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
53
+ </analyzer>
54
+ </fieldType>
55
+
56
+ <fieldType name="textTight" class="solr.TextField" positionIncrementGap="100" >
57
+ <analyzer>
58
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
59
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
60
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
61
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
62
+ <filter class="solr.LowerCaseFilterFactory"/>
63
+ <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
64
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
65
+ </analyzer>
66
+ </fieldType>
67
+
68
+ <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
69
+ <analyzer>
70
+ <tokenizer class="solr.KeywordTokenizerFactory"/>
71
+ <filter class="solr.LowerCaseFilterFactory" />
72
+ <filter class="solr.TrimFilterFactory" />
73
+ <filter class="solr.PatternReplaceFilterFactory"
74
+ pattern="([^a-z])" replacement="" replace="all"
75
+ />
76
+ </analyzer>
77
+ </fieldType>
78
+
79
+ <fieldtype name="ignored" stored="false" indexed="false" class="solr.StrField" />
80
+
81
+ </types>
82
+
83
+ <!-- For complete comments from the Solr project example schema.xml:
84
+ http://svn.apache.org/viewvc/lucene/dev/trunk/solr/example/solr/conf/schema.xml?view=markup
85
+ See also:
86
+ http://wiki.apache.org/solr/SchemaXml
87
+ -->
88
+ <fields>
89
+
90
+ <field name="id" type="string" indexed="true" stored="true" required="true" />
91
+ <field name="text" type="text" indexed="true" stored="true" multiValued="true"/>
92
+ <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
93
+
94
+ <!-- format is used for facet, display, and choosing which partial to use for the show view, so it must be stored and indexed -->
95
+ <field name="format" type="string" indexed="true" stored="true"/>
96
+ <!-- pub_date is assumed by Blacklight's default configuration, so we must define it here to avoid errors -->
97
+ <field name="pub_date" type="string" indexed="true" stored="true" multiValued="true"/>
98
+
99
+ <dynamicField name="*_i" type="sint" indexed="true" stored="true"/>
100
+ <dynamicField name="*_s" type="string" indexed="true" stored="true" multiValued="true"/>
101
+ <dynamicField name="*_l" type="slong" indexed="true" stored="true"/>
102
+ <dynamicField name="*_t" type="text" indexed="true" stored="true" multiValued="true"/>
103
+ <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
104
+ <dynamicField name="*_f" type="sfloat" indexed="true" stored="true"/>
105
+ <dynamicField name="*_d" type="sdouble" indexed="true" stored="true"/>
106
+ <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
107
+
108
+ <dynamicField name="random*" type="random" />
109
+ <!-- FIXME: Solr can't sort on a multivalued field -->
110
+ <dynamicField name="*_sort" type="string" indexed="true" stored="false" multiValued="true"/>
111
+ <!-- FIXME: generally, facet fields are not stored -->
112
+ <dynamicField name="*_facet" type="string" indexed="true" stored="true" multiValued="true" />
113
+ <dynamicField name="*_display" type="string" indexed="false" stored="true" multiValued="true" />
114
+
115
+ </fields>
116
+
117
+ <uniqueKey>id</uniqueKey>
118
+ <defaultSearchField>text</defaultSearchField>
119
+ <solrQueryParser defaultOperator="AND" />
120
+ <copyField source="*_facet" dest="text" />
121
+ <copyField source="*_t" dest="text" />
122
+ <copyField source="*_t" dest="*_s" />
123
+ <copyField source="*_s" dest="text" />
124
+
125
+ </schema>
data/config/solrconfig.xml CHANGED
@@ -1,1858 +1,1882 @@
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
- For more details about configurations options that may appear in
21
- this file, see http://wiki.apache.org/solr/SolrConfigXml.
22
- -->
23
- <config>
24
- <!-- In all configuration below, a prefix of "solr." for class names
25
- is an alias that causes solr to search appropriate packages,
26
- including org.apache.solr.(search|update|request|core|analysis)
27
-
28
- You may also specify a fully qualified Java classname if you
29
- have your own custom plugins.
30
- -->
31
-
32
- <!-- Set this to 'false' if you want solr to continue working after
33
- it has encountered an severe configuration error. In a
34
- production environment, you may want solr to keep working even
35
- if one handler is mis-configured.
36
-
37
- You may also set this to false using by setting the system
38
- property:
39
-
40
- -Dsolr.abortOnConfigurationError=false
41
- -->
42
- <abortOnConfigurationError>${solr.abortOnConfigurationError:false}</abortOnConfigurationError>
43
-
44
- <!-- Controls what version of Lucene various components of Solr
45
- adhere to. Generally, you want to use the latest version to
46
- get all bug fixes and improvements. It is highly recommended
47
- that you fully re-index after changing this setting as it can
48
- affect both how text is indexed and queried.
49
- -->
50
- <luceneMatchVersion>LUCENE_36</luceneMatchVersion>
51
-
52
- <!-- lib directives can be used to instruct Solr to load an Jars
53
- identified and use them to resolve any "plugins" specified in
54
- your solrconfig.xml or schema.xml (ie: Analyzers, Request
55
- Handlers, etc...).
56
-
57
- All directories and paths are resolved relative to the
58
- instanceDir.
59
-
60
- If a "./lib" directory exists in your instanceDir, all files
61
- found in it are included as if you had used the following
62
- syntax...
63
-
64
- <lib dir="./lib" />
65
- -->
66
-
67
- <!-- A dir option by itself adds any files found in the directory to
68
- the classpath, this is useful for including all jars in a
69
- directory.
70
- -->
71
-
72
- <!-- When a regex is specified in addition to a directory, only the
73
- files in that directory which completely match the regex
74
- (anchored on both ends) will be included.
75
- -->
76
- <!-- If a dir option (with or without a regex) is used and nothing
77
- is found that matches, it will be ignored
78
- -->
79
- <!-- an exact path can be used to specify a specific file. This
80
- will cause a serious error to be logged if it can't be loaded.
81
- -->
82
-
83
- <!-- Data Directory
84
-
85
- Used to specify an alternate directory to hold all index data
86
- other than the default ./data under the Solr home. If
87
- replication is in use, this should match the replication
88
- configuration.
89
- -->
90
- <dataDir>${solr.data.dir:}</dataDir>
91
-
92
-
93
- <!-- The DirectoryFactory to use for indexes.
94
-
95
- solr.StandardDirectoryFactory, the default, is filesystem
96
- based. solr.RAMDirectoryFactory is memory based, not
97
- persistent, and doesn't work with replication.
98
- -->
99
- <directoryFactory name="DirectoryFactory"
100
- class="${solr.directoryFactory:solr.StandardDirectoryFactory}"/>
101
-
102
-
103
- <!-- Index Defaults
104
-
105
- Values here affect all index writers and act as a default
106
- unless overridden.
107
-
108
- WARNING: See also the <mainIndex> section below for parameters
109
- that overfor Solr's main Lucene index.
110
- -->
111
- <indexDefaults>
112
-
113
- <useCompoundFile>false</useCompoundFile>
114
-
115
- <mergeFactor>10</mergeFactor>
116
- <!-- Sets the amount of RAM that may be used by Lucene indexing
117
- for buffering added documents and deletions before they are
118
- flushed to the Directory. -->
119
- <ramBufferSizeMB>32</ramBufferSizeMB>
120
- <!-- If both ramBufferSizeMB and maxBufferedDocs is set, then
121
- Lucene will flush based on whichever limit is hit first.
122
- -->
123
- <!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
124
-
125
- <maxFieldLength>10000</maxFieldLength>
126
- <writeLockTimeout>1000</writeLockTimeout>
127
-
128
- <!-- Expert: Merge Policy
129
-
130
- The Merge Policy in Lucene controls how merging is handled by
131
- Lucene. The default in Solr 3.3 is TieredMergePolicy.
132
-
133
- The default in 2.3 was the LogByteSizeMergePolicy,
134
- previous versions used LogDocMergePolicy.
135
-
136
- LogByteSizeMergePolicy chooses segments to merge based on
137
- their size. The Lucene 2.2 default, LogDocMergePolicy chose
138
- when to merge based on number of documents
139
-
140
- Other implementations of MergePolicy must have a no-argument
141
- constructor
142
- -->
143
- <!--
144
- <mergePolicy class="org.apache.lucene.index.TieredMergePolicy"/>
145
- -->
146
-
147
- <!-- Expert: Merge Scheduler
148
-
149
- The Merge Scheduler in Lucene controls how merges are
150
- performed. The ConcurrentMergeScheduler (Lucene 2.3 default)
151
- can perform merges in the background using separate threads.
152
- The SerialMergeScheduler (Lucene 2.2 default) does not.
153
- -->
154
- <!--
155
- <mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler"/>
156
- -->
157
-
158
- <!-- LockFactory
159
-
160
- This option specifies which Lucene LockFactory implementation
161
- to use.
162
-
163
- single = SingleInstanceLockFactory - suggested for a
164
- read-only index or when there is no possibility of
165
- another process trying to modify the index.
166
- native = NativeFSLockFactory - uses OS native file locking.
167
- Do not use when multiple solr webapps in the same
168
- JVM are attempting to share a single index.
169
- simple = SimpleFSLockFactory - uses a plain file for locking
170
-
171
- (For backwards compatibility with Solr 1.2, 'simple' is the
172
- default if not specified.)
173
-
174
- More details on the nuances of each LockFactory...
175
- http://wiki.apache.org/lucene-java/AvailableLockFactories
176
- -->
177
- <lockType>native</lockType>
178
-
179
- <!-- Expert: Controls how often Lucene loads terms into memory
180
- Default is 128 and is likely good for most everyone.
181
- -->
182
- <!-- <termIndexInterval>256</termIndexInterval> -->
183
- </indexDefaults>
184
-
185
- <!-- Main Index
186
-
187
- Values here override the values in the <indexDefaults> section
188
- for the main on disk index.
189
- -->
190
- <mainIndex>
191
-
192
- <useCompoundFile>false</useCompoundFile>
193
- <ramBufferSizeMB>32</ramBufferSizeMB>
194
- <mergeFactor>10</mergeFactor>
195
-
196
- <!-- Unlock On Startup
197
-
198
- If true, unlock any held write or commit locks on startup.
199
- This defeats the locking mechanism that allows multiple
200
- processes to safely access a lucene index, and should be used
201
- with care.
202
-
203
- This is not needed if lock type is 'none' or 'single'
204
- -->
205
- <unlockOnStartup>false</unlockOnStartup>
206
-
207
- <!-- If true, IndexReaders will be reopened (often more efficient)
208
- instead of closed and then opened.
209
- -->
210
- <reopenReaders>true</reopenReaders>
211
-
212
- <!-- Commit Deletion Policy
213
-
214
- Custom deletion policies can specified here. The class must
215
- implement org.apache.lucene.index.IndexDeletionPolicy.
216
-
217
- http://lucene.apache.org/java/2_9_1/api/all/org/apache/lucene/index/IndexDeletionPolicy.html
218
-
219
- The standard Solr IndexDeletionPolicy implementation supports
220
- deleting index commit points on number of commits, age of
221
- commit point and optimized status.
222
-
223
- The latest commit point should always be preserved regardless
224
- of the criteria.
225
- -->
226
- <deletionPolicy class="solr.SolrDeletionPolicy">
227
- <!-- The number of commit points to be kept -->
228
- <str name="maxCommitsToKeep">1</str>
229
- <!-- The number of optimized commit points to be kept -->
230
- <str name="maxOptimizedCommitsToKeep">0</str>
231
- <!--
232
- Delete all commit points once they have reached the given age.
233
- Supports DateMathParser syntax e.g.
234
- -->
235
- <!--
236
- <str name="maxCommitAge">30MINUTES</str>
237
- <str name="maxCommitAge">1DAY</str>
238
- -->
239
- </deletionPolicy>
240
-
241
- <!-- Lucene Infostream
242
-
243
- To aid in advanced debugging, Lucene provides an "InfoStream"
244
- of detailed information when indexing.
245
-
246
- Setting The value to true will instruct the underlying Lucene
247
- IndexWriter to write its debugging info the specified file
248
- -->
249
- <infoStream file="INFOSTREAM.txt">false</infoStream>
250
-
251
- </mainIndex>
252
-
253
- <!-- JMX
254
-
255
- This example enables JMX if and only if an existing MBeanServer
256
- is found, use this if you want to configure JMX through JVM
257
- parameters. Remove this to disable exposing Solr configuration
258
- and statistics to JMX.
259
-
260
- For more details see http://wiki.apache.org/solr/SolrJmx
261
- -->
262
- <jmx />
263
- <!-- If you want to connect to a particular server, specify the
264
- agentId
265
- -->
266
- <!-- <jmx agentId="myAgent" /> -->
267
- <!-- If you want to start a new MBeanServer, specify the serviceUrl -->
268
- <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
269
- -->
270
-
271
- <!-- The default high-performance update handler -->
272
- <updateHandler class="solr.DirectUpdateHandler2">
273
-
274
- <!-- AutoCommit
275
-
276
- Perform a <commit/> automatically under certain conditions.
277
- Instead of enabling autoCommit, consider using "commitWithin"
278
- when adding documents.
279
-
280
- http://wiki.apache.org/solr/UpdateXmlMessages
281
-
282
- maxDocs - Maximum number of documents to add since the last
283
- commit before automatically triggering a new commit.
284
-
285
- maxTime - Maximum amount of time that is allowed to pass
286
- since a document was added before automaticly
287
- triggering a new commit.
288
- -->
289
- <!--
290
- <autoCommit>
291
- <maxDocs>10000</maxDocs>
292
- <maxTime>1000</maxTime>
293
- </autoCommit>
294
- -->
295
-
296
- <!-- Update Related Event Listeners
297
-
298
- Various IndexWriter related events can trigger Listeners to
299
- take actions.
300
-
301
- postCommit - fired after every commit or optimize command
302
- postOptimize - fired after every optimize command
303
- -->
304
- <!-- The RunExecutableListener executes an external command from a
305
- hook such as postCommit or postOptimize.
306
-
307
- exe - the name of the executable to run
308
- dir - dir to use as the current working directory. (default=".")
309
- wait - the calling thread waits until the executable returns.
310
- (default="true")
311
- args - the arguments to pass to the program. (default is none)
312
- env - environment variables to set. (default is none)
313
- -->
314
- <!-- This example shows how RunExecutableListener could be used
315
- with the script based replication...
316
- http://wiki.apache.org/solr/CollectionDistribution
317
- -->
318
- <!--
319
- <listener event="postCommit" class="solr.RunExecutableListener">
320
- <str name="exe">solr/bin/snapshooter</str>
321
- <str name="dir">.</str>
322
- <bool name="wait">true</bool>
323
- <arr name="args"> <str>arg1</str> <str>arg2</str> </arr>
324
- <arr name="env"> <str>MYVAR=val1</str> </arr>
325
- </listener>
326
- -->
327
- </updateHandler>
328
-
329
- <!-- IndexReaderFactory
330
-
331
- Use the following format to specify a custom IndexReaderFactory,
332
- which allows for alternate IndexReader implementations.
333
-
334
- ** Experimental Feature **
335
-
336
- Please note - Using a custom IndexReaderFactory may prevent
337
- certain other features from working. The API to
338
- IndexReaderFactory may change without warning or may even be
339
- removed from future releases if the problems cannot be
340
- resolved.
341
-
342
-
343
- ** Features that may not work with custom IndexReaderFactory **
344
-
345
- The ReplicationHandler assumes a disk-resident index. Using a
346
- custom IndexReader implementation may cause incompatibility
347
- with ReplicationHandler and may cause replication to not work
348
- correctly. See SOLR-1366 for details.
349
-
350
- -->
351
- <!--
352
- <indexReaderFactory name="IndexReaderFactory" class="package.class">
353
- <str name="someArg">Some Value</str>
354
- </indexReaderFactory >
355
- -->
356
- <!-- By explicitly declaring the Factory, the termIndexDivisor can
357
- be specified.
358
- -->
359
- <!--
360
- <indexReaderFactory name="IndexReaderFactory"
361
- class="solr.StandardIndexReaderFactory">
362
- <int name="setTermIndexDivisor">12</int>
363
- </indexReaderFactory >
364
- -->
365
-
366
-
367
- <query>
368
- <!-- Max Boolean Clauses
369
-
370
- Maximum number of clauses in each BooleanQuery, an exception
371
- is thrown if exceeded.
372
-
373
- ** WARNING **
374
-
375
- This option actually modifies a global Lucene property that
376
- will affect all SolrCores. If multiple solrconfig.xml files
377
- disagree on this property, the value at any given moment will
378
- be based on the last SolrCore to be initialized.
379
-
380
- -->
381
- <maxBooleanClauses>1024</maxBooleanClauses>
382
-
383
-
384
- <!-- Solr Internal Query Caches
385
-
386
- There are two implementations of cache available for Solr,
387
- LRUCache, based on a synchronized LinkedHashMap, and
388
- FastLRUCache, based on a ConcurrentHashMap.
389
-
390
- FastLRUCache has faster gets and slower puts in single
391
- threaded operation and thus is generally faster than LRUCache
392
- when the hit ratio of the cache is high (> 75%), and may be
393
- faster under other scenarios on multi-cpu systems.
394
- -->
395
-
396
- <!-- Filter Cache
397
-
398
- Cache used by SolrIndexSearcher for filters (DocSets),
399
- unordered sets of *all* documents that match a query. When a
400
- new searcher is opened, its caches may be prepopulated or
401
- "autowarmed" using data from caches in the old searcher.
402
- autowarmCount is the number of items to prepopulate. For
403
- LRUCache, the autowarmed items will be the most recently
404
- accessed items.
405
-
406
- Parameters:
407
- class - the SolrCache implementation LRUCache or
408
- (LRUCache or FastLRUCache)
409
- size - the maximum number of entries in the cache
410
- initialSize - the initial capacity (number of entries) of
411
- the cache. (see java.util.HashMap)
412
- autowarmCount - the number of entries to prepopulate from
413
- and old cache.
414
- -->
415
- <filterCache class="solr.FastLRUCache"
416
- size="512"
417
- initialSize="512"
418
- autowarmCount="0"/>
419
-
420
- <!-- Query Result Cache
421
-
422
- Caches results of searches - ordered lists of document ids
423
- (DocList) based on a query, a sort, and the range of documents requested.
424
- -->
425
- <queryResultCache class="solr.LRUCache"
426
- size="512"
427
- initialSize="512"
428
- autowarmCount="0"/>
429
-
430
- <!-- Document Cache
431
-
432
- Caches Lucene Document objects (the stored fields for each
433
- document). Since Lucene internal document ids are transient,
434
- this cache will not be autowarmed.
435
- -->
436
- <documentCache class="solr.LRUCache"
437
- size="512"
438
- initialSize="512"
439
- autowarmCount="0"/>
440
-
441
- <!-- Field Value Cache
442
-
443
- Cache used to hold field values that are quickly accessible
444
- by document id. The fieldValueCache is created by default
445
- even if not configured here.
446
- -->
447
- <!--
448
- <fieldValueCache class="solr.FastLRUCache"
449
- size="512"
450
- autowarmCount="128"
451
- showItems="32" />
452
- -->
453
-
454
- <!-- Custom Cache
455
-
456
- Example of a generic cache. These caches may be accessed by
457
- name through SolrIndexSearcher.getCache(),cacheLookup(), and
458
- cacheInsert(). The purpose is to enable easy caching of
459
- user/application level data. The regenerator argument should
460
- be specified as an implementation of solr.CacheRegenerator
461
- if autowarming is desired.
462
- -->
463
- <!--
464
- <cache name="myUserCache"
465
- class="solr.LRUCache"
466
- size="4096"
467
- initialSize="1024"
468
- autowarmCount="1024"
469
- regenerator="com.mycompany.MyRegenerator"
470
- />
471
- -->
472
-
473
-
474
- <!-- Lazy Field Loading
475
-
476
- If true, stored fields that are not requested will be loaded
477
- lazily. This can result in a significant speed improvement
478
- if the usual case is to not load all stored fields,
479
- especially if the skipped fields are large compressed text
480
- fields.
481
- -->
482
- <enableLazyFieldLoading>true</enableLazyFieldLoading>
483
-
484
- <!-- Use Filter For Sorted Query
485
-
486
- A possible optimization that attempts to use a filter to
487
- satisfy a search. If the requested sort does not include
488
- score, then the filterCache will be checked for a filter
489
- matching the query. If found, the filter will be used as the
490
- source of document ids, and then the sort will be applied to
491
- that.
492
-
493
- For most situations, this will not be useful unless you
494
- frequently get the same search repeatedly with different sort
495
- options, and none of them ever use "score"
496
- -->
497
- <!--
498
- <useFilterForSortedQuery>true</useFilterForSortedQuery>
499
- -->
500
-
501
- <!-- Result Window Size
502
-
503
- An optimization for use with the queryResultCache. When a search
504
- is requested, a superset of the requested number of document ids
505
- are collected. For example, if a search for a particular query
506
- requests matching documents 10 through 19, and queryWindowSize is 50,
507
- then documents 0 through 49 will be collected and cached. Any further
508
- requests in that range can be satisfied via the cache.
509
- -->
510
- <queryResultWindowSize>20</queryResultWindowSize>
511
-
512
- <!-- Maximum number of documents to cache for any entry in the
513
- queryResultCache.
514
- -->
515
- <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
516
-
517
- <!-- Query Related Event Listeners
518
-
519
- Various IndexSearcher related events can trigger Listeners to
520
- take actions.
521
-
522
- newSearcher - fired whenever a new searcher is being prepared
523
- and there is a current searcher handling requests (aka
524
- registered). It can be used to prime certain caches to
525
- prevent long request times for certain requests.
526
-
527
- firstSearcher - fired whenever a new searcher is being
528
- prepared but there is no current registered searcher to handle
529
- requests or to gain autowarming data from.
530
-
531
-
532
- -->
533
- <!-- QuerySenderListener takes an array of NamedList and executes a
534
- local query request for each NamedList in sequence.
535
- -->
536
- <listener event="newSearcher" class="solr.QuerySenderListener">
537
- <arr name="queries">
538
- <!--
539
- <lst><str name="q">solr</str><str name="sort">price asc</str></lst>
540
- <lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
541
- -->
542
- </arr>
543
- </listener>
544
- <listener event="firstSearcher" class="solr.QuerySenderListener">
545
- <arr name="queries">
546
- <lst>
547
- <str name="q">static firstSearcher warming in solrconfig.xml</str>
548
- </lst>
549
- </arr>
550
- </listener>
551
-
552
- <!-- Use Cold Searcher
553
-
554
- If a search request comes in and there is no current
555
- registered searcher, then immediately register the still
556
- warming searcher and use it. If "false" then all requests
557
- will block until the first searcher is done warming.
558
- -->
559
- <useColdSearcher>false</useColdSearcher>
560
-
561
- <!-- Max Warming Searchers
562
-
563
- Maximum number of searchers that may be warming in the
564
- background concurrently. An error is returned if this limit
565
- is exceeded.
566
-
567
- Recommend values of 1-2 for read-only slaves, higher for
568
- masters w/o cache warming.
569
- -->
570
- <maxWarmingSearchers>2</maxWarmingSearchers>
571
-
572
- </query>
573
-
574
-
575
- <!-- Request Dispatcher
576
-
577
- This section contains instructions for how the SolrDispatchFilter
578
- should behave when processing requests for this SolrCore.
579
-
580
- handleSelect affects the behavior of requests such as /select?qt=XXX
581
-
582
- handleSelect="true" will cause the SolrDispatchFilter to process
583
- the request and will result in consistent error handling and
584
- formatting for all types of requests.
585
-
586
- handleSelect="false" will cause the SolrDispatchFilter to
587
- ignore "/select" requests and fallback to using the legacy
588
- SolrServlet and it's Solr 1.1 style error formatting
589
- -->
590
- <requestDispatcher handleSelect="true" >
591
- <!-- Request Parsing
592
-
593
- These settings indicate how Solr Requests may be parsed, and
594
- what restrictions may be placed on the ContentStreams from
595
- those requests
596
-
597
- enableRemoteStreaming - enables use of the stream.file
598
- and stream.url parameters for specifying remote streams.
599
-
600
- multipartUploadLimitInKB - specifies the max size of
601
- Multipart File Uploads that Solr will allow in a Request.
602
-
603
- *** WARNING ***
604
- The settings below authorize Solr to fetch remote files, You
605
- should make sure your system has some authentication before
606
- using enableRemoteStreaming="true"
607
-
608
- -->
609
- <requestParsers enableRemoteStreaming="true"
610
- multipartUploadLimitInKB="2048000" />
611
-
612
- <!-- HTTP Caching
613
-
614
- Set HTTP caching related parameters (for proxy caches and clients).
615
-
616
- The options below instruct Solr not to output any HTTP Caching
617
- related headers
618
- -->
619
- <httpCaching never304="true" />
620
- <!-- If you include a <cacheControl> directive, it will be used to
621
- generate a Cache-Control header (as well as an Expires header
622
- if the value contains "max-age=")
623
-
624
- By default, no Cache-Control header is generated.
625
-
626
- You can use the <cacheControl> option even if you have set
627
- never304="true"
628
- -->
629
- <!--
630
- <httpCaching never304="true" >
631
- <cacheControl>max-age=30, public</cacheControl>
632
- </httpCaching>
633
- -->
634
- <!-- To enable Solr to respond with automatically generated HTTP
635
- Caching headers, and to response to Cache Validation requests
636
- correctly, set the value of never304="false"
637
-
638
- This will cause Solr to generate Last-Modified and ETag
639
- headers based on the properties of the Index.
640
-
641
- The following options can also be specified to affect the
642
- values of these headers...
643
-
644
- lastModFrom - the default value is "openTime" which means the
645
- Last-Modified value (and validation against If-Modified-Since
646
- requests) will all be relative to when the current Searcher
647
- was opened. You can change it to lastModFrom="dirLastMod" if
648
- you want the value to exactly correspond to when the physical
649
- index was last modified.
650
-
651
- etagSeed="..." is an option you can change to force the ETag
652
- header (and validation against If-None-Match requests) to be
653
- different even if the index has not changed (ie: when making
654
- significant changes to your config file)
655
-
656
- (lastModifiedFrom and etagSeed are both ignored if you use
657
- the never304="true" option)
658
- -->
659
- <!--
660
- <httpCaching lastModifiedFrom="openTime"
661
- etagSeed="Solr">
662
- <cacheControl>max-age=30, public</cacheControl>
663
- </httpCaching>
664
- -->
665
- </requestDispatcher>
666
-
667
- <!-- Request Handlers
668
-
669
- http://wiki.apache.org/solr/SolrRequestHandler
670
-
671
- incoming queries will be dispatched to the correct handler
672
- based on the path or the qt (query type) param.
673
-
674
- Names starting with a '/' are accessed with the a path equal to
675
- the registered name. Names without a leading '/' are accessed
676
- with: http://host/app/[core/]select?qt=name
677
-
678
- If a /select request is processed with out a qt param
679
- specified, the requestHandler that declares default="true" will
680
- be used.
681
-
682
- If a Request Handler is declared with startup="lazy", then it will
683
- not be initialized until the first request that uses it.
684
-
685
- -->
686
-
687
- <!-- SearchHandler
688
-
689
- http://wiki.apache.org/solr/SearchHandler
690
-
691
- For processing Search Queries, the primary Request Handler
692
- provided with Solr is "SearchHandler" It delegates to a sequent
693
- of SearchComponents (see below) and supports distributed
694
- queries across multiple shards
695
- -->
696
- <requestHandler name="standard" class="solr.SearchHandler" default="true">
697
- <!-- default values for query parameters -->
698
- <lst name="defaults">
699
- <str name="echoParams">explicit</str>
700
- <!--
701
- <int name="rows">10</int>
702
- <str name="fl">*</str>
703
- <str name="version">2.1</str>
704
- -->
705
- </lst>
706
- </requestHandler>
707
- <!-- SearchHandler
708
-
709
- http://wiki.apache.org/solr/SearchHandler
710
-
711
- For processing Search Queries, the primary Request Handler
712
- provided with Solr is "SearchHandler" It delegates to a sequent
713
- of SearchComponents (see below) and supports distributed
714
- queries across multiple shards
715
- -->
716
- <requestHandler name="search" class="solr.SearchHandler" default="true">
717
- <!-- default values for query parameters can be specified, these
718
- will be overridden by parameters in the request
719
- -->
720
- <lst name="defaults">
721
- <str name="defType">dismax</str>
722
- <str name="echoParams">explicit</str>
723
- <int name="rows">10</int>
724
-
725
- <str name="q.alt">*:*</str>
726
- <str name="mm">2&lt;-1 5&lt;-2 6&lt;90%</str>
727
-
728
- <!-- this qf and pf are used by default, if not otherwise specified by
729
- client. The default blacklight_config will use these for the
730
- "keywords" search. See the author_qf/author_pf, title_qf, etc
731
- below, which the default blacklight_config will specify for
732
- those searches. You may also be interested in:
733
- http://wiki.apache.org/solr/LocalParams
734
- -->
735
-
736
- <str name="qf">
737
- title_unstem_search^100000
738
- subtitle_unstem_search^50000
739
- title_t^25000
740
- subtitle_t^10000
741
- title_addl_unstem_search^5000
742
- title_addl_t^2500
743
- title_added_entry_unstem_search^1500
744
- title_added_entry_t^1250
745
- subject_topic_unstem_search^1000
746
- subject_unstem_search^750
747
- subject_topic_facet^625
748
- subject_t^500
749
- author_unstem_search^250
750
- author_addl_unstem_search^250
751
- author_t^100
752
- author_addl_t^50
753
- subject_addl_unstem_search^250
754
- subject_addl_t^50
755
- title_series_unstem_search^25
756
- title_series_t^10
757
- isbn_t
758
- issn_t
759
- category_facet
760
- text
761
- </str>
762
- <str name="pf">
763
- title_unstem_search^1000000
764
- subtitle_unstem_search^500000
765
- title_t^250000
766
- subtitle_t^100000
767
- title_addl_unstem_search^50000
768
- title_addl_t^25000
769
- title_added_entry_unstem_search^15000
770
- title_added_entry_t^12500
771
- subject_topic_unstem_search^10000
772
- subject_unstem_search^7500
773
- subject_topic_facet^6250
774
- subject_t^5000
775
- author_unstem_search^2500
776
- author_addl_unstem_search^2500
777
- author_t^1000
778
- author_addl_t^500
779
- subject_addl_unstem_search^2500
780
- subject_addl_t^500
781
- title_series_unstem_search^250
782
- title_series_t^100
783
- text^10
784
- </str>
785
- <str name="author_qf">
786
- author_unstem_search^200
787
- author_addl_unstem_search^50
788
- author_t^20
789
- author_addl_t
790
- </str>
791
- <str name="author_pf">
792
- author_unstem_search^2000
793
- author_addl_unstem_search^500
794
- author_t^200
795
- author_addl_t^10
796
- </str>
797
- <str name="title_qf">
798
- title_unstem_search^50000
799
- subtitle_unstem_search^25000
800
- title_addl_unstem_search^10000
801
- title_t^5000
802
- subtitle_t^2500
803
- title_addl_t^100
804
- title_added_entry_unstem_search^50
805
- title_added_entry_t^10
806
- title_series_unstem_search^5
807
- title_series_t
808
- </str>
809
- <str name="title_pf">
810
- title_unstem_search^500000
811
- subtitle_unstem_search^250000
812
- title_addl_unstem_search^100000
813
- title_t^50000
814
- subtitle_t^25000
815
- title_addl_t^1000
816
- title_added_entry_unstem_search^500
817
- title_added_entry_t^100
818
- title_series_t^50
819
- title_series_unstem_search^10
820
- </str>
821
- <str name="subject_qf">
822
- subject_topic_unstem_search^200
823
- subject_unstem_search^125
824
- subject_topic_facet^100
825
- subject_t^50
826
- subject_addl_unstem_search^10
827
- subject_addl_t
828
- </str>
829
- <str name="subject_pf">
830
- subject_topic_unstem_search^2000
831
- subject_unstem_search^1250
832
- subject_t^1000
833
- subject_topic_facet^500
834
- subject_addl_unstem_search^100
835
- subject_addl_t^10
836
- </str>
837
-
838
- <int name="ps">3</int>
839
- <float name="tie">0.01</float>
840
-
841
- <!-- NOT using marc_display because it is large and will slow things down for search results -->
842
- <str name="fl">
843
- id,
844
- score,
845
- author_display,
846
- author_vern_display,
847
- format,
848
- isbn_t,
849
- issn_t,
850
- category_facet,
851
- language_facet,
852
- lc_callnum_display,
853
- material_type_display,
854
- published_display,
855
- published_vern_display,
856
- pub_date,
857
- title_display,
858
- title_vern_display,
859
- subject_topic_facet,
860
- subject_geo_facet,
861
- subject_era_facet,
862
- subtitle_display,
863
- subtitle_vern_display,
864
- url_fulltext_display,
865
- url_suppl_display,
866
- </str>
867
-
868
- <str name="facet">true</str>
869
- <str name="facet.mincount">1</str>
870
- <str name="facet.limit">-1</str>
871
- <str name="facet.sort">index</str>
872
- <str name="facet.field">format</str>
873
- <str name="facet.field">lc_1letter_facet</str>
874
- <str name="facet.field">lc_alpha_facet</str>
875
- <str name="facet.field">lc_b4cutter_facet</str>
876
- <str name="facet.field">language_facet</str>
877
- <str name="facet.field">pub_date</str>
878
- <str name="facet.field">subject_era_facet</str>
879
- <str name="facet.field">subject_geo_facet</str>
880
- <str name="facet.field">subject_topic_facet</str>
881
-
882
- <str name="f.provider_facet.facet.sort">count</str>
883
-
884
- <str name="spellcheck">true</str>
885
- <str name="spellcheck.dictionary">default</str>
886
- <str name="spellcheck.onlyMorePopular">true</str>
887
- <str name="spellcheck.extendedResults">true</str>
888
- <str name="spellcheck.collate">false</str>
889
- <str name="spellcheck.count">5</str>
890
-
891
- </lst>
892
- <!-- In addition to defaults, "appends" params can be specified
893
- to identify values which should be appended to the list of
894
- multi-val params from the query (or the existing "defaults").
895
- -->
896
- <!-- In this example, the param "fq=instock:true" would be appended to
897
- any query time fq params the user may specify, as a mechanism for
898
- partitioning the index, independent of any user selected filtering
899
- that may also be desired (perhaps as a result of faceted searching).
900
-
901
- NOTE: there is *absolutely* nothing a client can do to prevent these
902
- "appends" values from being used, so don't use this mechanism
903
- unless you are sure you always want it.
904
- -->
905
- <!--
906
- <lst name="appends">
907
- <str name="fq">inStock:true</str>
908
- </lst>
909
- -->
910
- <!-- "invariants" are a way of letting the Solr maintainer lock down
911
- the options available to Solr clients. Any params values
912
- specified here are used regardless of what values may be specified
913
- in either the query, the "defaults", or the "appends" params.
914
-
915
- In this example, the facet.field and facet.query params would
916
- be fixed, limiting the facets clients can use. Faceting is
917
- not turned on by default - but if the client does specify
918
- facet=true in the request, these are the only facets they
919
- will be able to see counts for; regardless of what other
920
- facet.field or facet.query params they may specify.
921
-
922
- NOTE: there is *absolutely* nothing a client can do to prevent these
923
- "invariants" values from being used, so don't use this mechanism
924
- unless you are sure you always want it.
925
- -->
926
- <!--
927
- <lst name="invariants">
928
- <str name="facet.field">cat</str>
929
- <str name="facet.field">manu_exact</str>
930
- <str name="facet.query">price:[* TO 500]</str>
931
- <str name="facet.query">price:[500 TO *]</str>
932
- </lst>
933
- -->
934
- <!-- If the default list of SearchComponents is not desired, that
935
- list can either be overridden completely, or components can be
936
- prepended or appended to the default list. (see below)
937
- -->
938
- <!--
939
- <arr name="components">
940
- <str>nameOfCustomComponent1</str>
941
- <str>nameOfCustomComponent2</str>
942
- </arr>
943
- -->
944
- <arr name="last-components">
945
- <str>spellcheck</str>
946
- </arr>
947
-
948
- </requestHandler>
949
-
950
- <!-- for requests to get a single document; use id=666 instead of q=id:666 -->
951
- <requestHandler name="document" class="solr.SearchHandler" >
952
- <lst name="defaults">
953
- <str name="echoParams">all</str>
954
- <str name="fl">*</str>
955
- <str name="rows">1</str>
956
- <str name="q">{!raw f=id v=$id}</str> <!-- use id=666 instead of q=id:666 -->
957
- </lst>
958
- </requestHandler>
959
-
960
- <!-- For Advanced Search -->
961
- <requestHandler name="advanced" class="solr.SearchHandler" >
962
- <lst name="defaults">
963
- <str name="defType">lucene</str>
964
- <str name="echoParams">explicit</str>
965
- <str name="sort">score desc, pub_date_sort desc, title_sort asc</str>
966
- <str name="df">text</str>
967
- <str name="q.op">AND</str>
968
- <str name="qs">1</str>
969
-
970
- <!-- used for dismax query parser -->
971
- <str name="mm">1</str>
972
- <str name="ps">3</str>
973
- <float name="tie">0.01</float>
974
-
975
- <!-- for user query terms in author text box -->
976
- <str name="qf_author">
977
- author_unstem_search^200
978
- author_addl_unstem_search^50
979
- author_t^20
980
- author_addl_t
981
- </str>
982
- <str name="pf_author">
983
- author_unstem_search^2000
984
- author_addl_unstem_search^500
985
- author_t^200
986
- author_addl_t^10
987
- </str>
988
-
989
- <!-- for user query terms in title text box -->
990
- <str name="qf_title">
991
- title_unstem_search^50000
992
- subtitle_unstem_search^25000
993
- title_addl_unstem_search^10000
994
- title_t^5000
995
- subtitle_t^2500
996
- title_addl_t^100
997
- title_added_entry_unstem_search^50
998
- title_added_entry_t^10
999
- title_series_unstem_search^5
1000
- title_series_t
1001
- </str>
1002
- <str name="pf_title">
1003
- title_unstem_search^500000
1004
- subtitle_unstem_search^250000
1005
- title_addl_unstem_search^100000
1006
- title_t^50000
1007
- subtitle_t^25000
1008
- title_addl_t^1000
1009
- title_added_entry_unstem_search^500
1010
- title_added_entry_t^100
1011
- title_series_t^50
1012
- title_series_unstem_search^10
1013
- </str>
1014
-
1015
- <!-- for user query terms in subject text box -->
1016
- <str name="qf_subject">
1017
- subject_topic_unstem_search^200
1018
- subject_unstem_search^125
1019
- subject_topic_facet^100
1020
- subject_t^50
1021
- subject_addl_unstem_search^10
1022
- subject_addl_t
1023
- </str>
1024
- <str name="pf_subject">
1025
- subject_topic_unstem_search^2000
1026
- subject_unstem_search^1250
1027
- subject_t^1000
1028
- subject_topic_facet^500
1029
- subject_addl_unstem_search^100
1030
- subject_addl_t^10
1031
- </str>
1032
-
1033
- <!-- for user query terms in number text box -->
1034
- <str name="qf_number">isbn_t</str>
1035
-
1036
- <!-- for user query terms in keyword text box -->
1037
- <str name="qf_keyword">text</str>
1038
- <str name="pf_keyword">text^10</str>
1039
-
1040
- <!-- NOT using marc_display because it is large and will slow things down for search results -->
1041
- <str name="fl">
1042
- id,
1043
- score,
1044
- author_display,
1045
- author_vern_display,
1046
- format,
1047
- isbn_t,
1048
- issn_t,
1049
- category_facet,
1050
- language_facet,
1051
- lc_callnum_display,
1052
- material_type_display,
1053
- published_display,
1054
- published_vern_display,
1055
- pub_date,
1056
- title_display,
1057
- title_vern_display,
1058
- subject_topic_facet,
1059
- subject_geo_facet,
1060
- subject_era_facet,
1061
- subtitle_display,
1062
- subtitle_vern_display,
1063
- url_fulltext_display,
1064
- url_suppl_display,
1065
- </str>
1066
-
1067
- <str name="facet">true</str>
1068
- <str name="facet.mincount">1</str>
1069
- <str name="facet.limit">10</str>
1070
- <str name="facet.field">format</str>
1071
- <str name="facet.field">lc_1letter_facet</str>
1072
- <str name="facet.field">lc_alpha_facet</str>
1073
- <str name="facet.field">lc_b4cutter_facet</str>
1074
- <str name="facet.field">language_facet</str>
1075
- <str name="facet.field">pub_date</str>
1076
- <str name="facet.field">subject_era_facet</str>
1077
- <str name="facet.field">subject_geo_facet</str>
1078
- <str name="facet.field">subject_topic_facet</str>
1079
-
1080
- <str name="spellcheck">true</str>
1081
- <str name="spellcheck.dictionary">subject</str>
1082
- <str name="spellcheck.onlyMorePopular">true</str>
1083
- <str name="spellcheck.extendedResults">true</str>
1084
- <str name="spellcheck.collate">false</str>
1085
- <str name="spellcheck.count">5</str>
1086
- </lst>
1087
- <arr name="last-components">
1088
- <str>spellcheck</str>
1089
- </arr>
1090
- </requestHandler>
1091
-
1092
-
1093
- <!-- XML Update Request Handler.
1094
-
1095
- http://wiki.apache.org/solr/UpdateXmlMessages
1096
-
1097
- The canonical Request Handler for Modifying the Index through
1098
- commands specified using XML.
1099
-
1100
- Note: Since solr1.1 requestHandlers requires a valid content
1101
- type header if posted in the body. For example, curl now
1102
- requires: -H 'Content-type:text/xml; charset=utf-8'
1103
- -->
1104
- <requestHandler name="/update"
1105
- class="solr.XmlUpdateRequestHandler">
1106
- <!-- See below for information on defining
1107
- updateRequestProcessorChains that can be used by name
1108
- on each Update Request
1109
- -->
1110
- <!--
1111
- <lst name="defaults">
1112
- <str name="update.chain">dedupe</str>
1113
- </lst>
1114
- -->
1115
- </requestHandler>
1116
- <!-- Binary Update Request Handler
1117
- http://wiki.apache.org/solr/javabin
1118
- -->
1119
- <requestHandler name="/update/javabin"
1120
- class="solr.BinaryUpdateRequestHandler" />
1121
-
1122
- <!-- CSV Update Request Handler
1123
- http://wiki.apache.org/solr/UpdateCSV
1124
- -->
1125
- <requestHandler name="/update/csv"
1126
- class="solr.CSVRequestHandler"
1127
- startup="lazy" />
1128
-
1129
- <!-- JSON Update Request Handler
1130
- http://wiki.apache.org/solr/UpdateJSON
1131
- -->
1132
- <requestHandler name="/update/json"
1133
- class="solr.JsonUpdateRequestHandler"
1134
- startup="lazy" />
1135
-
1136
- <!-- Solr Cell Update Request Handler
1137
-
1138
- http://wiki.apache.org/solr/ExtractingRequestHandler
1139
-
1140
- -->
1141
- <requestHandler name="/update/extract"
1142
- startup="lazy"
1143
- class="solr.extraction.ExtractingRequestHandler" >
1144
- <lst name="defaults">
1145
- <!-- All the main content goes into "text"... if you need to return
1146
- the extracted text or do highlighting, use a stored field. -->
1147
- <str name="fmap.content">text</str>
1148
- <str name="lowernames">true</str>
1149
- <str name="uprefix">ignored_</str>
1150
-
1151
- <!-- capture link hrefs but ignore div attributes -->
1152
- <str name="captureAttr">true</str>
1153
- <str name="fmap.a">links</str>
1154
- <str name="fmap.div">ignored_</str>
1155
- </lst>
1156
- </requestHandler>
1157
-
1158
- <!-- Field Analysis Request Handler
1159
-
1160
- RequestHandler that provides much the same functionality as
1161
- analysis.jsp. Provides the ability to specify multiple field
1162
- types and field names in the same request and outputs
1163
- index-time and query-time analysis for each of them.
1164
-
1165
- Request parameters are:
1166
- analysis.fieldname - field name whose analyzers are to be used
1167
-
1168
- analysis.fieldtype - field type whose analyzers are to be used
1169
- analysis.fieldvalue - text for index-time analysis
1170
- q (or analysis.q) - text for query time analysis
1171
- analysis.showmatch (true|false) - When set to true and when
1172
- query analysis is performed, the produced tokens of the
1173
- field value analysis will be marked as "matched" for every
1174
- token that is produces by the query analysis
1175
- -->
1176
- <requestHandler name="/analysis/field"
1177
- startup="lazy"
1178
- class="solr.FieldAnalysisRequestHandler" />
1179
-
1180
-
1181
- <!-- Document Analysis Handler
1182
-
1183
- http://wiki.apache.org/solr/AnalysisRequestHandler
1184
-
1185
- An analysis handler that provides a breakdown of the analysis
1186
- process of provided docuemnts. This handler expects a (single)
1187
- content stream with the following format:
1188
-
1189
- <docs>
1190
- <doc>
1191
- <field name="id">1</field>
1192
- <field name="name">The Name</field>
1193
- <field name="text">The Text Value</field>
1194
- </doc>
1195
- <doc>...</doc>
1196
- <doc>...</doc>
1197
- ...
1198
- </docs>
1199
-
1200
- Note: Each document must contain a field which serves as the
1201
- unique key. This key is used in the returned response to associate
1202
- an analysis breakdown to the analyzed document.
1203
-
1204
- Like the FieldAnalysisRequestHandler, this handler also supports
1205
- query analysis by sending either an "analysis.query" or "q"
1206
- request parameter that holds the query text to be analyzed. It
1207
- also supports the "analysis.showmatch" parameter which when set to
1208
- true, all field tokens that match the query tokens will be marked
1209
- as a "match".
1210
- -->
1211
- <requestHandler name="/analysis/document"
1212
- class="solr.DocumentAnalysisRequestHandler"
1213
- startup="lazy" />
1214
-
1215
- <!-- Admin Handlers
1216
-
1217
- Admin Handlers - This will register all the standard admin
1218
- RequestHandlers.
1219
- -->
1220
- <requestHandler name="/admin/"
1221
- class="solr.admin.AdminHandlers" />
1222
- <!-- This single handler is equivalent to the following... -->
1223
- <!--
1224
- <requestHandler name="/admin/luke" class="solr.admin.LukeRequestHandler" />
1225
- <requestHandler name="/admin/system" class="solr.admin.SystemInfoHandler" />
1226
- <requestHandler name="/admin/plugins" class="solr.admin.PluginInfoHandler" />
1227
- <requestHandler name="/admin/threads" class="solr.admin.ThreadDumpHandler" />
1228
- <requestHandler name="/admin/properties" class="solr.admin.PropertiesRequestHandler" />
1229
- <requestHandler name="/admin/file" class="solr.admin.ShowFileRequestHandler" >
1230
- -->
1231
- <!-- If you wish to hide files under ${solr.home}/conf, explicitly
1232
- register the ShowFileRequestHandler using:
1233
- -->
1234
- <!--
1235
- <requestHandler name="/admin/file"
1236
- class="solr.admin.ShowFileRequestHandler" >
1237
- <lst name="invariants">
1238
- <str name="hidden">synonyms.txt</str>
1239
- <str name="hidden">anotherfile.txt</str>
1240
- </lst>
1241
- </requestHandler>
1242
- -->
1243
-
1244
- <!-- ping/healthcheck -->
1245
- <requestHandler name="/admin/ping" class="solr.PingRequestHandler">
1246
- <lst name="defaults">
1247
- <str name="qt">search</str>
1248
- <str name="q">solrpingquery</str>
1249
- <str name="echoParams">all</str>
1250
- </lst>
1251
- </requestHandler>
1252
-
1253
- <!-- Echo the request contents back to the client -->
1254
- <requestHandler name="/debug/dump" class="solr.DumpRequestHandler" >
1255
- <lst name="defaults">
1256
- <str name="echoParams">explicit</str>
1257
- <str name="echoHandler">true</str>
1258
- </lst>
1259
- </requestHandler>
1260
-
1261
- <!-- Solr Replication
1262
-
1263
- The SolrReplicationHandler supports replicating indexes from a
1264
- "master" used for indexing and "salves" used for queries.
1265
-
1266
- http://wiki.apache.org/solr/SolrReplication
1267
-
1268
- In the example below, remove the <lst name="master"> section if
1269
- this is just a slave and remove the <lst name="slave"> section
1270
- if this is just a master.
1271
- -->
1272
- <!--
1273
- <requestHandler name="/replication" class="solr.ReplicationHandler" >
1274
- <lst name="master">
1275
- <str name="replicateAfter">commit</str>
1276
- <str name="replicateAfter">startup</str>
1277
- <str name="confFiles">schema.xml,stopwords.txt</str>
1278
- </lst>
1279
- <lst name="slave">
1280
- <str name="masterUrl">http://localhost:8983/solr/replication</str>
1281
- <str name="pollInterval">00:00:60</str>
1282
- </lst>
1283
- </requestHandler>
1284
- -->
1285
-
1286
- <!-- Search Components
1287
-
1288
- Search components are registered to SolrCore and used by
1289
- instances of SearchHandler (which can access them by name)
1290
-
1291
- By default, the following components are available:
1292
-
1293
- <searchComponent name="query" class="solr.QueryComponent" />
1294
- <searchComponent name="facet" class="solr.FacetComponent" />
1295
- <searchComponent name="mlt" class="solr.MoreLikeThisComponent" />
1296
- <searchComponent name="highlight" class="solr.HighlightComponent" />
1297
- <searchComponent name="stats" class="solr.StatsComponent" />
1298
- <searchComponent name="debug" class="solr.DebugComponent" />
1299
-
1300
- Default configuration in a requestHandler would look like:
1301
-
1302
- <arr name="components">
1303
- <str>query</str>
1304
- <str>facet</str>
1305
- <str>mlt</str>
1306
- <str>highlight</str>
1307
- <str>stats</str>
1308
- <str>debug</str>
1309
- </arr>
1310
-
1311
- If you register a searchComponent to one of the standard names,
1312
- that will be used instead of the default.
1313
-
1314
- To insert components before or after the 'standard' components, use:
1315
-
1316
- <arr name="first-components">
1317
- <str>myFirstComponentName</str>
1318
- </arr>
1319
-
1320
- <arr name="last-components">
1321
- <str>myLastComponentName</str>
1322
- </arr>
1323
-
1324
- NOTE: The component registered with the name "debug" will
1325
- always be executed after the "last-components"
1326
-
1327
- -->
1328
-
1329
- <!-- Spell Check
1330
-
1331
- The spell check component can return a list of alternative spelling
1332
- suggestions.
1333
-
1334
- http://wiki.apache.org/solr/SpellCheckComponent
1335
- -->
1336
- <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
1337
-
1338
- <str name="queryAnalyzerFieldType">textSpell</str>
1339
-
1340
- <!-- Multiple "Spell Checkers" can be declared and used by this
1341
- component
1342
- -->
1343
-
1344
- <!-- a spellchecker built from a field of the main index, and
1345
- written to disk
1346
- -->
1347
- <lst name="spellchecker">
1348
- <str name="name">default</str>
1349
- <str name="field">spell</str>
1350
- <str name="spellcheckIndexDir">./spell</str>
1351
- <str name="buildOnOptimize">true</str>
1352
- </lst>
1353
- <lst name="spellchecker">
1354
- <str name="name">author</str>
1355
- <str name="field">author_spell</str>
1356
- <str name="spellcheckIndexDir">./spell_author</str>
1357
- <str name="accuracy">0.7</str>
1358
- <str name="buildOnOptimize">true</str>
1359
- </lst>
1360
- <lst name="spellchecker">
1361
- <str name="name">subject</str>
1362
- <str name="field">subject_spell</str>
1363
- <str name="spellcheckIndexDir">./spell_subject</str>
1364
- <str name="accuracy">0.7</str>
1365
- <str name="buildOnOptimize">true</str>
1366
- </lst>
1367
- <lst name="spellchecker">
1368
- <str name="name">title</str>
1369
- <str name="field">title_spell</str>
1370
- <str name="spellcheckIndexDir">./spell_title</str>
1371
- <str name="accuracy">0.7</str>
1372
- <str name="buildOnOptimize">true</str>
1373
- </lst>
1374
-
1375
- <!-- a spellchecker that uses a different distance measure -->
1376
- <!--
1377
- <lst name="spellchecker">
1378
- <str name="name">jarowinkler</str>
1379
- <str name="field">spell</str>
1380
- <str name="distanceMeasure">
1381
- org.apache.lucene.search.spell.JaroWinklerDistance
1382
- </str>
1383
- <str name="spellcheckIndexDir">spellcheckerJaro</str>
1384
- </lst>
1385
- -->
1386
-
1387
- <!-- a spellchecker that use an alternate comparator
1388
-
1389
- comparatorClass be one of:
1390
- 1. score (default)
1391
- 2. freq (Frequency first, then score)
1392
- 3. A fully qualified class name
1393
- -->
1394
- <!--
1395
- <lst name="spellchecker">
1396
- <str name="name">freq</str>
1397
- <str name="field">lowerfilt</str>
1398
- <str name="spellcheckIndexDir">spellcheckerFreq</str>
1399
- <str name="comparatorClass">freq</str>
1400
- <str name="buildOnCommit">true</str>
1401
- -->
1402
-
1403
- <!-- A spellchecker that reads the list of words from a file -->
1404
- <!--
1405
- <lst name="spellchecker">
1406
- <str name="classname">solr.FileBasedSpellChecker</str>
1407
- <str name="name">file</str>
1408
- <str name="sourceLocation">spellings.txt</str>
1409
- <str name="characterEncoding">UTF-8</str>
1410
- <str name="spellcheckIndexDir">spellcheckerFile</str>
1411
- </lst>
1412
- -->
1413
- </searchComponent>
1414
-
1415
- <!-- A request handler for demonstrating the spellcheck component.
1416
-
1417
- NOTE: This is purely as an example. The whole purpose of the
1418
- SpellCheckComponent is to hook it into the request handler that
1419
- handles your normal user queries so that a separate request is
1420
- not needed to get suggestions.
1421
-
1422
- IN OTHER WORDS, THERE IS REALLY GOOD CHANCE THE SETUP BELOW IS
1423
- NOT WHAT YOU WANT FOR YOUR PRODUCTION SYSTEM!
1424
-
1425
- See http://wiki.apache.org/solr/SpellCheckComponent for details
1426
- on the request parameters.
1427
- -->
1428
- <requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
1429
- <lst name="defaults">
1430
- <str name="spellcheck.onlyMorePopular">false</str>
1431
- <str name="spellcheck.extendedResults">false</str>
1432
- <str name="spellcheck.count">1</str>
1433
- </lst>
1434
- <arr name="last-components">
1435
- <str>spellcheck</str>
1436
- </arr>
1437
- </requestHandler>
1438
-
1439
- <!-- Term Vector Component
1440
-
1441
- http://wiki.apache.org/solr/TermVectorComponent
1442
- -->
1443
- <searchComponent name="tvComponent" class="solr.TermVectorComponent"/>
1444
-
1445
- <!-- A request handler for demonstrating the term vector component
1446
-
1447
- This is purely as an example.
1448
-
1449
- In reality you will likely want to add the component to your
1450
- already specified request handlers.
1451
- -->
1452
- <requestHandler name="tvrh" class="solr.SearchHandler" startup="lazy">
1453
- <lst name="defaults">
1454
- <bool name="tv">true</bool>
1455
- </lst>
1456
- <arr name="last-components">
1457
- <str>tvComponent</str>
1458
- </arr>
1459
- </requestHandler>
1460
-
1461
- <!-- Clustering Component
1462
-
1463
- http://wiki.apache.org/solr/ClusteringComponent
1464
-
1465
- This relies on third party jars which are notincluded in the
1466
- release. To use this component (and the "/clustering" handler)
1467
- Those jars will need to be downloaded, and you'll need to set
1468
- the solr.cluster.enabled system property when running solr...
1469
-
1470
- java -Dsolr.clustering.enabled=true -jar start.jar
1471
- -->
1472
- <searchComponent name="clustering"
1473
- enable="${solr.clustering.enabled:false}"
1474
- class="solr.clustering.ClusteringComponent" >
1475
- <!-- Declare an engine -->
1476
- <lst name="engine">
1477
- <!-- The name, only one can be named "default" -->
1478
- <str name="name">default</str>
1479
-
1480
- <!-- Class name of Carrot2 clustering algorithm.
1481
-
1482
- Currently available algorithms are:
1483
-
1484
- * org.carrot2.clustering.lingo.LingoClusteringAlgorithm
1485
- * org.carrot2.clustering.stc.STCClusteringAlgorithm
1486
- * org.carrot2.clustering.kmeans.BisectingKMeansClusteringAlgorithm
1487
-
1488
- See http://project.carrot2.org/algorithms.html for the
1489
- algorithm's characteristics.
1490
- -->
1491
- <str name="carrot.algorithm">org.carrot2.clustering.lingo.LingoClusteringAlgorithm</str>
1492
-
1493
- <!-- Overriding values for Carrot2 default algorithm attributes.
1494
-
1495
- For a description of all available attributes, see:
1496
- http://download.carrot2.org/stable/manual/#chapter.components.
1497
- Use attribute key as name attribute of str elements
1498
- below. These can be further overridden for individual
1499
- requests by specifying attribute key as request parameter
1500
- name and attribute value as parameter value.
1501
- -->
1502
- <str name="LingoClusteringAlgorithm.desiredClusterCountBase">20</str>
1503
-
1504
- <!-- Location of Carrot2 lexical resources.
1505
-
1506
- A directory from which to load Carrot2-specific stop words
1507
- and stop labels. Absolute or relative to Solr config directory.
1508
- If a specific resource (e.g. stopwords.en) is present in the
1509
- specified dir, it will completely override the corresponding
1510
- default one that ships with Carrot2.
1511
-
1512
- For an overview of Carrot2 lexical resources, see:
1513
- http://download.carrot2.org/head/manual/#chapter.lexical-resources
1514
- -->
1515
- <str name="carrot.lexicalResourcesDir">clustering/carrot2</str>
1516
-
1517
- <!-- The language to assume for the documents.
1518
-
1519
- For a list of allowed values, see:
1520
- http://download.carrot2.org/stable/manual/#section.attribute.lingo.MultilingualClustering.defaultLanguage
1521
- -->
1522
- <str name="MultilingualClustering.defaultLanguage">ENGLISH</str>
1523
- </lst>
1524
- <lst name="engine">
1525
- <str name="name">stc</str>
1526
- <str name="carrot.algorithm">org.carrot2.clustering.stc.STCClusteringAlgorithm</str>
1527
- </lst>
1528
- </searchComponent>
1529
-
1530
- <!-- A request handler for demonstrating the clustering component
1531
-
1532
- This is purely as an example.
1533
-
1534
- In reality you will likely want to add the component to your
1535
- already specified request handlers.
1536
- -->
1537
- <requestHandler name="/clustering"
1538
- startup="lazy"
1539
- enable="${solr.clustering.enabled:false}"
1540
- class="solr.SearchHandler">
1541
- <lst name="defaults">
1542
- <bool name="clustering">true</bool>
1543
- <str name="clustering.engine">default</str>
1544
- <bool name="clustering.results">true</bool>
1545
- <!-- The title field -->
1546
- <str name="carrot.title">name</str>
1547
- <str name="carrot.url">id</str>
1548
- <!-- The field to cluster on -->
1549
- <str name="carrot.snippet">features</str>
1550
- <!-- produce summaries -->
1551
- <bool name="carrot.produceSummary">true</bool>
1552
- <!-- the maximum number of labels per cluster -->
1553
- <!--<int name="carrot.numDescriptions">5</int>-->
1554
- <!-- produce sub clusters -->
1555
- <bool name="carrot.outputSubClusters">false</bool>
1556
-
1557
- <str name="defType">edismax</str>
1558
- <str name="qf">
1559
- text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0 manu^1.1 cat^1.4
1560
- </str>
1561
- <str name="q.alt">*:*</str>
1562
- <str name="rows">10</str>
1563
- <str name="fl">*,score</str>
1564
- </lst>
1565
- <arr name="last-components">
1566
- <str>clustering</str>
1567
- </arr>
1568
- </requestHandler>
1569
-
1570
- <!-- Terms Component
1571
-
1572
- http://wiki.apache.org/solr/TermsComponent
1573
-
1574
- A component to return terms and document frequency of those
1575
- terms
1576
- -->
1577
- <searchComponent name="terms" class="solr.TermsComponent"/>
1578
-
1579
- <!-- A request handler for demonstrating the terms component -->
1580
- <requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
1581
- <lst name="defaults">
1582
- <bool name="terms">true</bool>
1583
- </lst>
1584
- <arr name="components">
1585
- <str>terms</str>
1586
- </arr>
1587
- </requestHandler>
1588
-
1589
-
1590
- <!-- Query Elevation Component
1591
-
1592
- http://wiki.apache.org/solr/QueryElevationComponent
1593
-
1594
- a search component that enables you to configure the top
1595
- results for a given query regardless of the normal lucene
1596
- scoring.
1597
- -->
1598
- <searchComponent name="elevator" class="solr.QueryElevationComponent" >
1599
- <!-- pick a fieldType to analyze queries -->
1600
- <str name="queryFieldType">string</str>
1601
- <str name="config-file">elevate.xml</str>
1602
- </searchComponent>
1603
-
1604
- <!-- A request handler for demonstrating the elevator component -->
1605
- <requestHandler name="/elevate" class="solr.SearchHandler" startup="lazy">
1606
- <lst name="defaults">
1607
- <str name="echoParams">explicit</str>
1608
- </lst>
1609
- <arr name="last-components">
1610
- <str>elevator</str>
1611
- </arr>
1612
- </requestHandler>
1613
-
1614
- <!-- Highlighting Component
1615
-
1616
- http://wiki.apache.org/solr/HighlightingParameters
1617
- -->
1618
- <searchComponent class="solr.HighlightComponent" name="highlight">
1619
- <highlighting>
1620
- <!-- Configure the standard fragmenter -->
1621
- <!-- This could most likely be commented out in the "default" case -->
1622
- <fragmenter name="gap"
1623
- default="true"
1624
- class="solr.highlight.GapFragmenter">
1625
- <lst name="defaults">
1626
- <int name="hl.fragsize">100</int>
1627
- </lst>
1628
- </fragmenter>
1629
-
1630
- <!-- A regular-expression-based fragmenter
1631
- (for sentence extraction)
1632
- -->
1633
- <fragmenter name="regex"
1634
- class="solr.highlight.RegexFragmenter">
1635
- <lst name="defaults">
1636
- <!-- slightly smaller fragsizes work better because of slop -->
1637
- <int name="hl.fragsize">70</int>
1638
- <!-- allow 50% slop on fragment sizes -->
1639
- <float name="hl.regex.slop">0.5</float>
1640
- <!-- a basic sentence pattern -->
1641
- <str name="hl.regex.pattern">[-\w ,/\n\&quot;&apos;]{20,200}</str>
1642
- </lst>
1643
- </fragmenter>
1644
-
1645
- <!-- Configure the standard formatter -->
1646
- <formatter name="html"
1647
- default="true"
1648
- class="solr.highlight.HtmlFormatter">
1649
- <lst name="defaults">
1650
- <str name="hl.simple.pre"><![CDATA[<em>]]></str>
1651
- <str name="hl.simple.post"><![CDATA[</em>]]></str>
1652
- </lst>
1653
- </formatter>
1654
-
1655
- <!-- Configure the standard encoder -->
1656
- <encoder name="html"
1657
- class="solr.highlight.HtmlEncoder" />
1658
-
1659
- <!-- Configure the standard fragListBuilder -->
1660
- <fragListBuilder name="simple"
1661
- default="true"
1662
- class="solr.highlight.SimpleFragListBuilder"/>
1663
-
1664
- <!-- Configure the single fragListBuilder -->
1665
- <fragListBuilder name="single"
1666
- class="solr.highlight.SingleFragListBuilder"/>
1667
-
1668
- <!-- default tag FragmentsBuilder -->
1669
- <fragmentsBuilder name="default"
1670
- default="true"
1671
- class="solr.highlight.ScoreOrderFragmentsBuilder">
1672
- <!--
1673
- <lst name="defaults">
1674
- <str name="hl.multiValuedSeparatorChar">/</str>
1675
- </lst>
1676
- -->
1677
- </fragmentsBuilder>
1678
-
1679
- <!-- multi-colored tag FragmentsBuilder -->
1680
- <fragmentsBuilder name="colored"
1681
- class="solr.highlight.ScoreOrderFragmentsBuilder">
1682
- <lst name="defaults">
1683
- <str name="hl.tag.pre"><![CDATA[
1684
- <b style="background:yellow">,<b style="background:lawgreen">,
1685
- <b style="background:aquamarine">,<b style="background:magenta">,
1686
- <b style="background:palegreen">,<b style="background:coral">,
1687
- <b style="background:wheat">,<b style="background:khaki">,
1688
- <b style="background:lime">,<b style="background:deepskyblue">]]></str>
1689
- <str name="hl.tag.post"><![CDATA[</b>]]></str>
1690
- </lst>
1691
- </fragmentsBuilder>
1692
-
1693
- <boundaryScanner name="default"
1694
- default="true"
1695
- class="solr.highlight.SimpleBoundaryScanner">
1696
- <lst name="defaults">
1697
- <str name="hl.bs.maxScan">10</str>
1698
- <str name="hl.bs.chars">.,!? &#9;&#10;&#13;</str>
1699
- </lst>
1700
- </boundaryScanner>
1701
-
1702
- <boundaryScanner name="breakIterator"
1703
- class="solr.highlight.BreakIteratorBoundaryScanner">
1704
- <lst name="defaults">
1705
- <!-- type should be one of CHARACTER, WORD(default), LINE and SENTENCE -->
1706
- <str name="hl.bs.type">WORD</str>
1707
- <!-- language and country are used when constructing Locale object. -->
1708
- <!-- And the Locale object will be used when getting instance of BreakIterator -->
1709
- <str name="hl.bs.language">en</str>
1710
- <str name="hl.bs.country">US</str>
1711
- </lst>
1712
- </boundaryScanner>
1713
- </highlighting>
1714
- </searchComponent>
1715
-
1716
- <!-- Update Processors
1717
-
1718
- Chains of Update Processor Factories for dealing with Update
1719
- Requests can be declared, and then used by name in Update
1720
- Request Processors
1721
-
1722
- http://wiki.apache.org/solr/UpdateRequestProcessor
1723
-
1724
- -->
1725
- <!-- Deduplication
1726
-
1727
- An example dedup update processor that creates the "id" field
1728
- on the fly based on the hash code of some other fields. This
1729
- example has overwriteDupes set to false since we are using the
1730
- id field as the signatureField and Solr will maintain
1731
- uniqueness based on that anyway.
1732
-
1733
- -->
1734
- <!--
1735
- <updateRequestProcessorChain name="dedupe">
1736
- <processor class="solr.processor.SignatureUpdateProcessorFactory">
1737
- <bool name="enabled">true</bool>
1738
- <str name="signatureField">id</str>
1739
- <bool name="overwriteDupes">false</bool>
1740
- <str name="fields">name,features,cat</str>
1741
- <str name="signatureClass">solr.processor.Lookup3Signature</str>
1742
- </processor>
1743
- <processor class="solr.LogUpdateProcessorFactory" />
1744
- <processor class="solr.RunUpdateProcessorFactory" />
1745
- </updateRequestProcessorChain>
1746
- -->
1747
-
1748
- <!--
1749
- This example update chain identifies the language of the incoming
1750
- documents using the langid contrib. The detected language is
1751
- written to field language_s. No field name mapping is done.
1752
- The fields used for detection are text, title, subject and description,
1753
- making this example suitable for detecting languages form full-text
1754
- rich documents injected via ExtractingRequestHandler.
1755
- See more about langId at http://wiki.apache.org/solr/LanguageDetection
1756
- -->
1757
- <!--
1758
- <updateRequestProcessorChain name="langid">
1759
- <processor class="org.apache.solr.update.processor.TikaLanguageIdentifierUpdateProcessorFactory">
1760
- <str name="langid.fl">text,title,subject,description</str>
1761
- <str name="langid.langField">language_s</str>
1762
- <str name="langid.fallback">en</str>
1763
- </processor>
1764
- <processor class="solr.LogUpdateProcessorFactory" />
1765
- <processor class="solr.RunUpdateProcessorFactory" />
1766
- </updateRequestProcessorChain>
1767
- -->
1768
-
1769
- <!-- Response Writers
1770
-
1771
- http://wiki.apache.org/solr/QueryResponseWriter
1772
-
1773
- Request responses will be written using the writer specified by
1774
- the 'wt' request parameter matching the name of a registered
1775
- writer.
1776
-
1777
- The "default" writer is the default and will be used if 'wt' is
1778
- not specified in the request.
1779
- -->
1780
- <!-- The following response writers are implicitly configured unless
1781
- overridden...
1782
- -->
1783
- <!--
1784
- <queryResponseWriter name="xml"
1785
- default="true"
1786
- class="solr.XMLResponseWriter" />
1787
- <queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
1788
- <queryResponseWriter name="python" class="solr.PythonResponseWriter"/>
1789
- <queryResponseWriter name="ruby" class="solr.RubyResponseWriter"/>
1790
- <queryResponseWriter name="php" class="solr.PHPResponseWriter"/>
1791
- <queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/>
1792
- <queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
1793
- -->
1794
-
1795
- <queryResponseWriter name="json" class="solr.JSONResponseWriter">
1796
- <!-- For the purposes of the tutorial, JSON responses are written as
1797
- plain text so that they are easy to read in *any* browser.
1798
- If you expect a MIME type of "application/json" just remove this override.
1799
- -->
1800
- <str name="content-type">text/plain; charset=UTF-8</str>
1801
- </queryResponseWriter>
1802
-
1803
- <!--
1804
- Custom response writers can be declared as needed...
1805
- -->
1806
- <!-- The solr.velocity.enabled flag is used by Solr's test cases so that this response writer is not
1807
- loaded (causing an error if contrib/velocity has not been built fully) -->
1808
- <!-- <queryResponseWriter name="velocity" class="solr.VelocityResponseWriter" enable="${solr.velocity.enabled:true}"/> -->
1809
- <queryResponseWriter name="velocity" class="solr.VelocityResponseWriter" enable="${solr.velocity.enabled:false}"/>
1810
-
1811
-
1812
- <!-- XSLT response writer transforms the XML output by any xslt file found
1813
- in Solr's conf/xslt directory. Changes to xslt files are checked for
1814
- every xsltCacheLifetimeSeconds.
1815
- -->
1816
- <queryResponseWriter name="xslt" class="solr.XSLTResponseWriter">
1817
- <int name="xsltCacheLifetimeSeconds">5</int>
1818
- </queryResponseWriter>
1819
-
1820
- <!-- Query Parsers
1821
-
1822
- http://wiki.apache.org/solr/SolrQuerySyntax
1823
-
1824
- Multiple QParserPlugins can be registered by name, and then
1825
- used in either the "defType" param for the QueryComponent (used
1826
- by SearchHandler) or in LocalParams
1827
- -->
1828
- <!-- example of registering a query parser -->
1829
- <!--
1830
- <queryParser name="myparser" class="com.mycompany.MyQParserPlugin"/>
1831
- -->
1832
-
1833
- <!-- Function Parsers
1834
-
1835
- http://wiki.apache.org/solr/FunctionQuery
1836
-
1837
- Multiple ValueSourceParsers can be registered by name, and then
1838
- used as function names when using the "func" QParser.
1839
- -->
1840
- <!-- example of registering a custom function parser -->
1841
- <!--
1842
- <valueSourceParser name="myfunc"
1843
- class="com.mycompany.MyValueSourceParser" />
1844
- -->
1845
-
1846
- <!-- Legacy config for the admin interface -->
1847
- <admin>
1848
- <defaultQuery>*:*</defaultQuery>
1849
-
1850
- <!-- configure a healthcheck file for servers behind a
1851
- loadbalancer
1852
- -->
1853
- <!--
1854
- <healthcheck type="file">server-enabled</healthcheck>
1855
- -->
1856
- </admin>
1857
-
1858
- </config>
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
+ For more details about configurations options that may appear in
21
+ this file, see http://wiki.apache.org/solr/SolrConfigXml.
22
+ -->
23
+ <config>
24
+ <!-- In all configuration below, a prefix of "solr." for class names
25
+ is an alias that causes solr to search appropriate packages,
26
+ including org.apache.solr.(search|update|request|core|analysis)
27
+
28
+ You may also specify a fully qualified Java classname if you
29
+ have your own custom plugins.
30
+ -->
31
+
32
+ <!-- Set this to 'false' if you want solr to continue working after
33
+ it has encountered an severe configuration error. In a
34
+ production environment, you may want solr to keep working even
35
+ if one handler is mis-configured.
36
+
37
+ You may also set this to false using by setting the system
38
+ property:
39
+
40
+ -Dsolr.abortOnConfigurationError=false
41
+ -->
42
+ <abortOnConfigurationError>${solr.abortOnConfigurationError:true}</abortOnConfigurationError>
43
+
44
+ <!-- Controls what version of Lucene various components of Solr
45
+ adhere to. Generally, you want to use the latest version to
46
+ get all bug fixes and improvements. It is highly recommended
47
+ that you fully re-index after changing this setting as it can
48
+ affect both how text is indexed and queried.
49
+ -->
50
+ <luceneMatchVersion>LUCENE_35</luceneMatchVersion>
51
+
52
+ <!-- lib directives can be used to instruct Solr to load an Jars
53
+ identified and use them to resolve any "plugins" specified in
54
+ your solrconfig.xml or schema.xml (ie: Analyzers, Request
55
+ Handlers, etc...).
56
+
57
+ All directories and paths are resolved relative to the
58
+ instanceDir.
59
+
60
+ If a "./lib" directory exists in your instanceDir, all files
61
+ found in it are included as if you had used the following
62
+ syntax...
63
+
64
+ <lib dir="./lib" />
65
+ -->
66
+
67
+ <!-- Blacklight jetty solr lib dirs -->
68
+ <lib dir="./contrib/extraction/lib" />
69
+ <lib dir="./contrib/clustering/lib/" />
70
+ <lib dir="./contrib/velocity/lib" />
71
+ <lib dir="./contrib/analysis-extras/lib" />
72
+ <lib dir="./contrib/analysis-extras/lucene-libs" />
73
+
74
+ <!-- A dir option by itself adds any files found in the directory to
75
+ the classpath, this is useful for including all jars in a
76
+ directory.
77
+ -->
78
+ <lib dir="../../contrib/extraction/lib" />
79
+ <lib dir="../../contrib/clustering/lib/" />
80
+ <lib dir="../../contrib/velocity/lib" />
81
+
82
+ <!-- When a regex is specified in addition to a directory, only the
83
+ files in that directory which completely match the regex
84
+ (anchored on both ends) will be included.
85
+ -->
86
+ <lib dir="../../dist/" regex="apache-solr-cell-\d.*\.jar" />
87
+ <lib dir="../../dist/" regex="apache-solr-clustering-\d.*\.jar" />
88
+ <lib dir="../../dist/" regex="apache-solr-dataimporthandler-\d.*\.jar" />
89
+ <lib dir="../../dist/" regex="apache-solr-langid-\d.*\.jar" />
90
+ <lib dir="../../dist/" regex="apache-solr-velocity-\d.*\.jar" />
91
+
92
+ <!-- If a dir option (with or without a regex) is used and nothing
93
+ is found that matches, it will be ignored
94
+ -->
95
+ <lib dir="../../contrib/clustering/lib/" />
96
+ <lib dir="/total/crap/dir/ignored" />
97
+
98
+ <!-- an exact path can be used to specify a specific file. This
99
+ will cause a serious error to be logged if it can't be loaded.
100
+ -->
101
+ <!--
102
+ <lib path="../a-jar-that-does-not-exist.jar" />
103
+ -->
104
+
105
+ <!-- Data Directory
106
+
107
+ Used to specify an alternate directory to hold all index data
108
+ other than the default ./data under the Solr home. If
109
+ replication is in use, this should match the replication
110
+ configuration.
111
+ -->
112
+ <dataDir>${solr.data.dir:}</dataDir>
113
+
114
+
115
+ <!-- The DirectoryFactory to use for indexes.
116
+
117
+ solr.StandardDirectoryFactory, the default, is filesystem
118
+ based. solr.RAMDirectoryFactory is memory based, not
119
+ persistent, and doesn't work with replication.
120
+ -->
121
+ <directoryFactory name="DirectoryFactory"
122
+ class="${solr.directoryFactory:solr.StandardDirectoryFactory}"/>
123
+
124
+
125
+ <!-- Index Defaults
126
+
127
+ Values here affect all index writers and act as a default
128
+ unless overridden.
129
+
130
+ WARNING: See also the <mainIndex> section below for parameters
131
+ that overfor Solr's main Lucene index.
132
+ -->
133
+ <indexDefaults>
134
+
135
+ <useCompoundFile>false</useCompoundFile>
136
+
137
+ <mergeFactor>10</mergeFactor>
138
+ <!-- Sets the amount of RAM that may be used by Lucene indexing
139
+ for buffering added documents and deletions before they are
140
+ flushed to the Directory. -->
141
+ <ramBufferSizeMB>32</ramBufferSizeMB>
142
+ <!-- If both ramBufferSizeMB and maxBufferedDocs is set, then
143
+ Lucene will flush based on whichever limit is hit first.
144
+ -->
145
+ <!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
146
+
147
+ <maxFieldLength>10000</maxFieldLength>
148
+ <writeLockTimeout>1000</writeLockTimeout>
149
+
150
+ <!-- Expert: Merge Policy
151
+
152
+ The Merge Policy in Lucene controls how merging is handled by
153
+ Lucene. The default in Solr 3.3 is TieredMergePolicy.
154
+
155
+ The default in 2.3 was the LogByteSizeMergePolicy,
156
+ previous versions used LogDocMergePolicy.
157
+
158
+ LogByteSizeMergePolicy chooses segments to merge based on
159
+ their size. The Lucene 2.2 default, LogDocMergePolicy chose
160
+ when to merge based on number of documents
161
+
162
+ Other implementations of MergePolicy must have a no-argument
163
+ constructor
164
+ -->
165
+ <!--
166
+ <mergePolicy class="org.apache.lucene.index.TieredMergePolicy"/>
167
+ -->
168
+
169
+ <!-- Expert: Merge Scheduler
170
+
171
+ The Merge Scheduler in Lucene controls how merges are
172
+ performed. The ConcurrentMergeScheduler (Lucene 2.3 default)
173
+ can perform merges in the background using separate threads.
174
+ The SerialMergeScheduler (Lucene 2.2 default) does not.
175
+ -->
176
+ <!--
177
+ <mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler"/>
178
+ -->
179
+
180
+ <!-- LockFactory
181
+
182
+ This option specifies which Lucene LockFactory implementation
183
+ to use.
184
+
185
+ single = SingleInstanceLockFactory - suggested for a
186
+ read-only index or when there is no possibility of
187
+ another process trying to modify the index.
188
+ native = NativeFSLockFactory - uses OS native file locking.
189
+ Do not use when multiple solr webapps in the same
190
+ JVM are attempting to share a single index.
191
+ simple = SimpleFSLockFactory - uses a plain file for locking
192
+
193
+ (For backwards compatibility with Solr 1.2, 'simple' is the
194
+ default if not specified.)
195
+
196
+ More details on the nuances of each LockFactory...
197
+ http://wiki.apache.org/lucene-java/AvailableLockFactories
198
+ -->
199
+ <lockType>native</lockType>
200
+
201
+ <!-- Expert: Controls how often Lucene loads terms into memory
202
+ Default is 128 and is likely good for most everyone.
203
+ -->
204
+ <!-- <termIndexInterval>256</termIndexInterval> -->
205
+ </indexDefaults>
206
+
207
+ <!-- Main Index
208
+
209
+ Values here override the values in the <indexDefaults> section
210
+ for the main on disk index.
211
+ -->
212
+ <mainIndex>
213
+
214
+ <useCompoundFile>false</useCompoundFile>
215
+ <ramBufferSizeMB>32</ramBufferSizeMB>
216
+ <mergeFactor>10</mergeFactor>
217
+
218
+ <!-- Unlock On Startup
219
+
220
+ If true, unlock any held write or commit locks on startup.
221
+ This defeats the locking mechanism that allows multiple
222
+ processes to safely access a lucene index, and should be used
223
+ with care.
224
+
225
+ This is not needed if lock type is 'none' or 'single'
226
+ -->
227
+ <unlockOnStartup>false</unlockOnStartup>
228
+
229
+ <!-- If true, IndexReaders will be reopened (often more efficient)
230
+ instead of closed and then opened.
231
+ -->
232
+ <reopenReaders>true</reopenReaders>
233
+
234
+ <!-- Commit Deletion Policy
235
+
236
+ Custom deletion policies can specified here. The class must
237
+ implement org.apache.lucene.index.IndexDeletionPolicy.
238
+
239
+ http://lucene.apache.org/java/2_9_1/api/all/org/apache/lucene/index/IndexDeletionPolicy.html
240
+
241
+ The standard Solr IndexDeletionPolicy implementation supports
242
+ deleting index commit points on number of commits, age of
243
+ commit point and optimized status.
244
+
245
+ The latest commit point should always be preserved regardless
246
+ of the criteria.
247
+ -->
248
+ <deletionPolicy class="solr.SolrDeletionPolicy">
249
+ <!-- The number of commit points to be kept -->
250
+ <str name="maxCommitsToKeep">1</str>
251
+ <!-- The number of optimized commit points to be kept -->
252
+ <str name="maxOptimizedCommitsToKeep">0</str>
253
+ <!--
254
+ Delete all commit points once they have reached the given age.
255
+ Supports DateMathParser syntax e.g.
256
+ -->
257
+ <!--
258
+ <str name="maxCommitAge">30MINUTES</str>
259
+ <str name="maxCommitAge">1DAY</str>
260
+ -->
261
+ </deletionPolicy>
262
+
263
+ <!-- Lucene Infostream
264
+
265
+ To aid in advanced debugging, Lucene provides an "InfoStream"
266
+ of detailed information when indexing.
267
+
268
+ Setting The value to true will instruct the underlying Lucene
269
+ IndexWriter to write its debugging info the specified file
270
+ -->
271
+ <infoStream file="INFOSTREAM.txt">false</infoStream>
272
+
273
+ </mainIndex>
274
+
275
+ <!-- JMX
276
+
277
+ This example enables JMX if and only if an existing MBeanServer
278
+ is found, use this if you want to configure JMX through JVM
279
+ parameters. Remove this to disable exposing Solr configuration
280
+ and statistics to JMX.
281
+
282
+ For more details see http://wiki.apache.org/solr/SolrJmx
283
+ -->
284
+ <jmx />
285
+ <!-- If you want to connect to a particular server, specify the
286
+ agentId
287
+ -->
288
+ <!-- <jmx agentId="myAgent" /> -->
289
+ <!-- If you want to start a new MBeanServer, specify the serviceUrl -->
290
+ <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
291
+ -->
292
+
293
+ <!-- The default high-performance update handler -->
294
+ <updateHandler class="solr.DirectUpdateHandler2">
295
+
296
+ <!-- AutoCommit
297
+
298
+ Perform a <commit/> automatically under certain conditions.
299
+ Instead of enabling autoCommit, consider using "commitWithin"
300
+ when adding documents.
301
+
302
+ http://wiki.apache.org/solr/UpdateXmlMessages
303
+
304
+ maxDocs - Maximum number of documents to add since the last
305
+ commit before automatically triggering a new commit.
306
+
307
+ maxTime - Maximum amount of time that is allowed to pass
308
+ since a document was added before automaticly
309
+ triggering a new commit.
310
+ -->
311
+ <!--
312
+ <autoCommit>
313
+ <maxDocs>10000</maxDocs>
314
+ <maxTime>1000</maxTime>
315
+ </autoCommit>
316
+ -->
317
+
318
+ <!-- Update Related Event Listeners
319
+
320
+ Various IndexWriter related events can trigger Listeners to
321
+ take actions.
322
+
323
+ postCommit - fired after every commit or optimize command
324
+ postOptimize - fired after every optimize command
325
+ -->
326
+ <!-- The RunExecutableListener executes an external command from a
327
+ hook such as postCommit or postOptimize.
328
+
329
+ exe - the name of the executable to run
330
+ dir - dir to use as the current working directory. (default=".")
331
+ wait - the calling thread waits until the executable returns.
332
+ (default="true")
333
+ args - the arguments to pass to the program. (default is none)
334
+ env - environment variables to set. (default is none)
335
+ -->
336
+ <!-- This example shows how RunExecutableListener could be used
337
+ with the script based replication...
338
+ http://wiki.apache.org/solr/CollectionDistribution
339
+ -->
340
+ <!--
341
+ <listener event="postCommit" class="solr.RunExecutableListener">
342
+ <str name="exe">solr/bin/snapshooter</str>
343
+ <str name="dir">.</str>
344
+ <bool name="wait">true</bool>
345
+ <arr name="args"> <str>arg1</str> <str>arg2</str> </arr>
346
+ <arr name="env"> <str>MYVAR=val1</str> </arr>
347
+ </listener>
348
+ -->
349
+ </updateHandler>
350
+
351
+ <!-- IndexReaderFactory
352
+
353
+ Use the following format to specify a custom IndexReaderFactory,
354
+ which allows for alternate IndexReader implementations.
355
+
356
+ ** Experimental Feature **
357
+
358
+ Please note - Using a custom IndexReaderFactory may prevent
359
+ certain other features from working. The API to
360
+ IndexReaderFactory may change without warning or may even be
361
+ removed from future releases if the problems cannot be
362
+ resolved.
363
+
364
+
365
+ ** Features that may not work with custom IndexReaderFactory **