sunspot_solr 2.0.0 → 2.1.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Binary file
@@ -236,7 +236,11 @@
236
236
  <dynamicField name="*_llm" stored="false" type="location" multiValued="true" indexed="true"/>
237
237
  <dynamicField name="*_lls" stored="true" type="location" multiValued="false" indexed="true"/>
238
238
  <dynamicField name="*_llms" stored="true" type="location" multiValued="true" indexed="true"/>
239
+
240
+ <!-- required by Solr 4 -->
241
+ <field name="_version_" type="string" indexed="true" stored="true" multiValued="false" />
239
242
  </fields>
243
+
240
244
  <!-- Field to use to determine and enforce document uniqueness.
241
245
  Unless this field is marked with required="false", it will be a required field
242
246
  -->
@@ -1,4 +1,4 @@
1
- <?xml version="1.0" encoding="UTF-8"?>
1
+ <?xml version="1.0" encoding="UTF-8" ?>
2
2
  <!--
3
3
  Licensed to the Apache Software Foundation (ASF) under one or more
4
4
  contributor license agreements. See the NOTICE file distributed with
@@ -15,920 +15,653 @@
15
15
  See the License for the specific language governing permissions and
16
16
  limitations under the License.
17
17
  -->
18
- <!--
19
- For more details about configurations options that may appear in this
20
- file, see http://wiki.apache.org/solr/SolrConfigXml.
21
18
 
22
- Specifically, the Solr Config can support XInclude, which may make it easier to manage
23
- the configuration. See https://issues.apache.org/jira/browse/SOLR-1167
19
+ <!--
20
+ For more details about configurations options that may appear in
21
+ this file, see http://wiki.apache.org/solr/SolrConfigXml.
24
22
  -->
25
23
  <config>
26
- <!-- Set this to 'false' if you want solr to continue working after it has
27
- encountered an severe configuration error. In a production environment,
28
- you may want solr to keep working even if one handler is mis-configured.
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)
29
27
 
30
- You may also set this to false using by setting the system property:
31
- -Dsolr.abortOnConfigurationError=false
32
- -->
33
- <abortOnConfigurationError>${solr.abortOnConfigurationError:true}</abortOnConfigurationError>
34
- <!-- lib directives can be used to instruct Solr to load an Jars identified
35
- and use them to resolve any "plugins" specified in your solrconfig.xml or
36
- schema.xml (ie: Analyzers, Request Handlers, etc...).
28
+ You may also specify a fully qualified Java classname if you
29
+ have your own custom plugins.
30
+ -->
31
+
32
+ <!-- Controls what version of Lucene various components of Solr
33
+ adhere to. Generally, you want to use the latest version to
34
+ get all bug fixes and improvements. It is highly recommended
35
+ that you fully re-index after changing this setting as it can
36
+ affect both how text is indexed and queried.
37
+ -->
38
+ <luceneMatchVersion>LUCENE_41</luceneMatchVersion>
39
+
40
+ <!-- <lib/> directives can be used to instruct Solr to load an Jars
41
+ identified and use them to resolve any "plugins" specified in
42
+ your solrconfig.xml or schema.xml (ie: Analyzers, Request
43
+ Handlers, etc...).
44
+
45
+ All directories and paths are resolved relative to the
46
+ instanceDir.
37
47
 
38
- All directories and paths are resolved relative the instanceDir.
48
+ Please note that <lib/> directives are processed in the order
49
+ that they appear in your solrconfig.xml file, and are "stacked"
50
+ on top of each other when building a ClassLoader - so if you have
51
+ plugin jars with dependencies on other jars, the "lower level"
52
+ dependency jars should be loaded first.
39
53
 
40
- If a "./lib" directory exists in your instanceDir, all files found in it
41
- are included as if you had used the following syntax...
54
+ If a "./lib" directory exists in your instanceDir, all files
55
+ found in it are included as if you had used the following
56
+ syntax...
42
57
 
43
58
  <lib dir="./lib" />
44
59
  -->
45
- <!-- A dir option by itself adds any files found in the directory to the
46
- classpath, this is useful for including all jars in a directory.
47
- -->
48
- <lib dir="../../contrib/extraction/lib"/>
49
- <!-- When a regex is specified in addition to a directory, only the files in that
50
- directory which completely match the regex (anchored on both ends)
51
- will be included.
52
- -->
53
- <lib dir="../../dist/" regex="apache-solr-cell-\d.*\.jar"/>
54
- <lib dir="../../dist/" regex="apache-solr-clustering-\d.*\.jar"/>
55
- <!-- If a dir option (with or without a regex) is used and nothing is found
56
- that matches, it will be ignored
57
- -->
58
- <lib dir="../../contrib/clustering/lib/downloads/"/>
59
- <lib dir="../../contrib/clustering/lib/"/>
60
- <lib dir="/total/crap/dir/ignored"/>
61
- <!-- an exact path can be used to specify a specific file. This will cause
62
- a serious error to be logged if it can't be loaded.
63
- <lib path="../a-jar-that-does-not-exist.jar" />
64
- -->
65
- <!-- Used to specify an alternate directory to hold all index data
66
- other than the default ./data under the Solr home.
67
- If replication is in use, this should match the replication configuration. -->
68
- <dataDir>${solr.data.dir:./solr/data}</dataDir>
69
- <!-- WARNING: this <indexDefaults> section only provides defaults for index writers
70
- in general. See also the <mainIndex> section after that when changing parameters
71
- for Solr's main Lucene index. -->
72
- <indexDefaults>
73
- <!-- Values here affect all index writers and act as a default unless overridden. -->
74
- <useCompoundFile>false</useCompoundFile>
75
- <mergeFactor>10</mergeFactor>
76
- <!-- If both ramBufferSizeMB and maxBufferedDocs is set, then Lucene will flush
77
- based on whichever limit is hit first. -->
78
- <!--<maxBufferedDocs>1000</maxBufferedDocs>-->
79
- <!-- Sets the amount of RAM that may be used by Lucene indexing
80
- for buffering added documents and deletions before they are
81
- flushed to the Directory. -->
82
- <ramBufferSizeMB>32</ramBufferSizeMB>
83
- <!-- <maxMergeDocs>2147483647</maxMergeDocs> -->
84
- <maxFieldLength>10000</maxFieldLength>
85
- <writeLockTimeout>1000</writeLockTimeout>
86
- <commitLockTimeout>10000</commitLockTimeout>
87
- <!--
88
- Expert: Turn on Lucene's auto commit capability. This causes intermediate
89
- segment flushes to write a new lucene index descriptor, enabling it to be
90
- opened by an external IndexReader. This can greatly slow down indexing
91
- speed. NOTE: Despite the name, this value does not have any relation to
92
- Solr's autoCommit functionality
93
- -->
94
- <!--<luceneAutoCommit>false</luceneAutoCommit>-->
95
- <!--
96
- Expert: The Merge Policy in Lucene controls how merging is handled by
97
- Lucene. The default in 2.3 is the LogByteSizeMergePolicy, previous
98
- versions used LogDocMergePolicy.
60
+ <dataDir>${solr.data.dir:}</dataDir>
99
61
 
100
- LogByteSizeMergePolicy chooses segments to merge based on their size. The
101
- Lucene 2.2 default, LogDocMergePolicy chose when to merge based on number
102
- of documents
103
62
 
104
- Other implementations of MergePolicy must have a no-argument constructor
105
- -->
106
- <!--<mergePolicy class="org.apache.lucene.index.LogByteSizeMergePolicy"/>-->
107
- <!--
108
- Expert:
109
- The Merge Scheduler in Lucene controls how merges are performed. The
110
- ConcurrentMergeScheduler (Lucene 2.3 default) can perform merges in the
111
- background using separate threads. The SerialMergeScheduler (Lucene 2.2
112
- default) does not.
113
- -->
114
- <!--<mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler"/>-->
115
- <!--
116
- This option specifies which Lucene LockFactory implementation to use.
117
-
118
- single = SingleInstanceLockFactory - suggested for a read-only index
119
- or when there is no possibility of another process trying
120
- to modify the index.
121
- native = NativeFSLockFactory - uses OS native file locking
122
- simple = SimpleFSLockFactory - uses a plain file for locking
123
-
124
- (For backwards compatibility with Solr 1.2, 'simple' is the default
125
- if not specified.)
126
- -->
127
- <lockType>native</lockType>
128
- <!--
129
- Expert:
130
- Controls how often Lucene loads terms into memory -->
131
- <!--<termIndexInterval>256</termIndexInterval>-->
132
- </indexDefaults>
133
- <mainIndex>
134
- <!-- options specific to the main on-disk lucene index -->
135
- <useCompoundFile>false</useCompoundFile>
136
- <ramBufferSizeMB>32</ramBufferSizeMB>
137
- <mergeFactor>10</mergeFactor>
138
- <!-- Deprecated -->
139
- <!--<maxBufferedDocs>1000</maxBufferedDocs>-->
140
- <!--<maxMergeDocs>2147483647</maxMergeDocs>-->
141
- <!-- inherit from indexDefaults <maxFieldLength>10000</maxFieldLength> -->
142
- <!-- If true, unlock any held write or commit locks on startup.
143
- This defeats the locking mechanism that allows multiple
144
- processes to safely access a lucene index, and should be
145
- used with care.
146
- This is not needed if lock type is 'none' or 'single'
147
- -->
148
- <unlockOnStartup>false</unlockOnStartup>
149
- <!-- If true, IndexReaders will be reopened (often more efficient) instead
150
- of closed and then opened. -->
151
- <reopenReaders>true</reopenReaders>
152
- <!--
153
- Expert:
154
- Controls how often Lucene loads terms into memory. Default is 128 and is likely good for most everyone. -->
155
- <!--<termIndexInterval>256</termIndexInterval>-->
156
- <!--
157
- Custom deletion policies can specified here. The class must
158
- implement org.apache.lucene.index.IndexDeletionPolicy.
63
+ <!-- The DirectoryFactory to use for indexes.
64
+
65
+ solr.StandardDirectoryFactory is filesystem
66
+ based and tries to pick the best implementation for the current
67
+ JVM and platform. solr.NRTCachingDirectoryFactory, the default,
68
+ wraps solr.StandardDirectoryFactory and caches small files in memory
69
+ for better NRT performance.
159
70
 
160
- http://lucene.apache.org/java/2_3_2/api/org/apache/lucene/index/IndexDeletionPolicy.html
71
+ One can force a particular implementation via solr.MMapDirectoryFactory,
72
+ solr.NIOFSDirectoryFactory, or solr.SimpleFSDirectoryFactory.
161
73
 
162
- The standard Solr IndexDeletionPolicy implementation supports deleting
163
- index commit points on number of commits, age of commit point and
164
- optimized status.
74
+ solr.RAMDirectoryFactory is memory based, not
75
+ persistent, and doesn't work with replication.
76
+ -->
77
+ <directoryFactory name="DirectoryFactory"
78
+ class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}"/>
165
79
 
166
- The latest commit point should always be preserved regardless
167
- of the criteria.
80
+ <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
81
+ Index Config - These settings control low-level behavior of indexing
82
+ Most example settings here show the default value, but are commented
83
+ out, to more easily see where customizations have been made.
84
+
85
+ Note: This replaces <indexDefaults> and <mainIndex> from older versions
86
+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
87
+ <indexConfig>
88
+ <!-- maxFieldLength was removed in 4.0. To get similar behavior, include a
89
+ LimitTokenCountFilterFactory in your fieldType definition. E.g.
90
+ <filter class="solr.LimitTokenCountFilterFactory" maxTokenCount="10000"/>
168
91
  -->
169
- <deletionPolicy class="solr.SolrDeletionPolicy">
170
- <!-- The number of commit points to be kept -->
171
- <str name="maxCommitsToKeep">1</str>
172
- <!-- The number of optimized commit points to be kept -->
173
- <str name="maxOptimizedCommitsToKeep">0</str>
174
- <!--
175
- Delete all commit points once they have reached the given age.
176
- Supports DateMathParser syntax e.g.
177
-
178
- <str name="maxCommitAge">30MINUTES</str>
179
- <str name="maxCommitAge">1DAY</str>
92
+ <!-- Maximum time to wait for a write lock (ms) for an IndexWriter. Default: 1000 -->
93
+ <!-- <writeLockTimeout>1000</writeLockTimeout> -->
94
+
95
+ <!-- The maximum number of simultaneous threads that may be
96
+ indexing documents at once in IndexWriter; if more than this
97
+ many threads arrive they will wait for others to finish.
98
+ Default in Solr/Lucene is 8. -->
99
+ <maxIndexingThreads>2</maxIndexingThreads>
100
+
101
+ <useCompoundFile>true</useCompoundFile>
102
+
103
+ <!-- ramBufferSizeMB sets the amount of RAM that may be used by Lucene
104
+ indexing for buffering added documents and deletions before they are
105
+ flushed to the Directory.
106
+ maxBufferedDocs sets a limit on the number of documents buffered
107
+ before flushing.
108
+ If both ramBufferSizeMB and maxBufferedDocs is set, then
109
+ Lucene will flush based on whichever limit is hit first. -->
110
+ <ramBufferSizeMB>20</ramBufferSizeMB> -->
111
+ <maxBufferedDocs>10000</maxBufferedDocs>
112
+
113
+ <!-- Expert: Merge Policy
114
+ The Merge Policy in Lucene controls how merging of segments is done.
115
+ The default since Solr/Lucene 3.3 is TieredMergePolicy.
116
+ The default since Lucene 2.3 was the LogByteSizeMergePolicy,
117
+ Even older versions of Lucene used LogDocMergePolicy.
180
118
  -->
181
- </deletionPolicy>
182
- <!-- To aid in advanced debugging, you may turn on IndexWriter debug logging.
183
- Setting to true will set the file that the underlying Lucene IndexWriter
184
- will write its debug infostream to. -->
185
- <infoStream file="INFOSTREAM.txt">false</infoStream>
186
- </mainIndex>
187
- <!-- Enables JMX if and only if an existing MBeanServer is found, use this
188
- if you want to configure JMX through JVM parameters. Remove this to disable
189
- exposing Solr configuration and statistics to JMX.
190
-
191
- If you want to connect to a particular server, specify the agentId
192
- e.g. <jmx agentId="myAgent" />
193
-
194
- If you want to start a new MBeanServer, specify the serviceUrl
195
- e.g <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
196
-
197
- For more details see http://wiki.apache.org/solr/SolrJmx
198
- -->
199
- <jmx/>
200
- <!-- the default high-performance update handler -->
119
+ <mergePolicy class="org.apache.lucene.index.TieredMergePolicy">
120
+ <int name="maxMergeAtOnce">4</int>
121
+ <int name="segmentsPerTier">4</int>
122
+ </mergePolicy>
123
+
124
+ <unlockOnStartup>true</unlockOnStartup>
125
+
126
+ </indexConfig>
127
+
201
128
  <updateHandler class="solr.DirectUpdateHandler2">
202
- <!-- A prefix of "solr." for class names is an alias that
203
- causes solr to search appropriate packages, including
204
- org.apache.solr.(search|update|request|core|analysis)
205
- -->
206
- <!-- Perform a <commit/> automatically under certain conditions:
207
- maxDocs - number of updates since last commit is greater than this
208
- maxTime - oldest uncommited update (in ms) is this long ago
209
- Instead of enabling autoCommit, consider using "commitWithin"
210
- when adding documents. http://wiki.apache.org/solr/UpdateXmlMessages
211
- <autoCommit>
212
- <maxDocs>10000</maxDocs>
213
- <maxTime>1000</maxTime>
214
- </autoCommit>
215
- -->
216
- <!-- The RunExecutableListener executes an external command from a
217
- hook such as postCommit or postOptimize.
218
- exe - the name of the executable to run
219
- dir - dir to use as the current working directory. default="."
220
- wait - the calling thread waits until the executable returns. default="true"
221
- args - the arguments to pass to the program. default=nothing
222
- env - environment variables to set. default=nothing
223
- -->
224
- <!-- A postCommit event is fired after every commit or optimize command
225
- <listener event="postCommit" class="solr.RunExecutableListener">
226
- <str name="exe">solr/bin/snapshooter</str>
227
- <str name="dir">.</str>
228
- <bool name="wait">true</bool>
229
- <arr name="args"> <str>arg1</str> <str>arg2</str> </arr>
230
- <arr name="env"> <str>MYVAR=val1</str> </arr>
231
- </listener>
232
- -->
233
- <!-- A postOptimize event is fired only after every optimize command
234
- <listener event="postOptimize" class="solr.RunExecutableListener">
235
- <str name="exe">snapshooter</str>
236
- <str name="dir">solr/bin</str>
237
- <bool name="wait">true</bool>
238
- </listener>
239
- -->
129
+
130
+ <!-- Enables a transaction log, used for real-time get, durability, and
131
+ and solr cloud replica recovery. The log can grow as big as
132
+ uncommitted changes to the index, so use of a hard autoCommit
133
+ is recommended (see below).
134
+ "dir" - the target directory for transaction logs, defaults to the
135
+ solr data directory. -->
136
+ <updateLog>
137
+ <str name="dir">${solr.ulog.dir:}</str>
138
+ </updateLog>
139
+
140
+ <autoCommit>
141
+ <maxTime>15000</maxTime>
142
+ <openSearcher>false</openSearcher>
143
+ </autoCommit>
144
+
145
+ <autoSoftCommit>
146
+ <maxTime>5000</maxTime>
147
+ </autoSoftCommit>
240
148
  </updateHandler>
241
- <!-- Use the following format to specify a custom IndexReaderFactory - allows for alternate
242
- IndexReader implementations.
243
-
244
- ** Experimental Feature **
245
- Please note - Using a custom IndexReaderFactory may prevent certain other features
246
- from working. The API to IndexReaderFactory may change without warning or may even
247
- be removed from future releases if the problems cannot be resolved.
248
-
249
- ** Features that may not work with custom IndexReaderFactory **
250
- The ReplicationHandler assumes a disk-resident index. Using a custom
251
- IndexReader implementation may cause incompatibility with ReplicationHandler and
252
- may cause replication to not work correctly. See SOLR-1366 for details.
253
-
254
- <indexReaderFactory name="IndexReaderFactory" class="package.class">
255
- Parameters as required by the implementation
256
- </indexReaderFactory >
257
- -->
258
- <!-- To set the termInfosIndexDivisor, do this: -->
259
- <!--<indexReaderFactory name="IndexReaderFactory" class="org.apache.solr.core.StandardIndexReaderFactory">
260
- <int name="termInfosIndexDivisor">12</int>
261
- </indexReaderFactory >-->
149
+
262
150
  <query>
263
- <!-- Maximum number of clauses in a boolean query... in the past, this affected
264
- range or prefix queries that expanded to big boolean queries - built in Solr
265
- query parsers no longer create queries with this limitation.
266
- An exception is thrown if exceeded. -->
267
151
  <maxBooleanClauses>1024</maxBooleanClauses>
268
- <!-- There are two implementations of cache available for Solr,
152
+
153
+
154
+ <!-- Solr Internal Query Caches
155
+
156
+ There are two implementations of cache available for Solr,
269
157
  LRUCache, based on a synchronized LinkedHashMap, and
270
- FastLRUCache, based on a ConcurrentHashMap. FastLRUCache has faster gets
271
- and slower puts in single threaded operation and thus is generally faster
272
- than LRUCache when the hit ratio of the cache is high (> 75%), and may be
273
- faster under other scenarios on multi-cpu systems. -->
274
- <!-- Cache used by SolrIndexSearcher for filters (DocSets),
275
- unordered sets of *all* documents that match a query.
276
- When a new searcher is opened, its caches may be prepopulated
277
- or "autowarmed" using data from caches in the old searcher.
278
- autowarmCount is the number of items to prepopulate. For LRUCache,
279
- the autowarmed items will be the most recently accessed items.
280
- Parameters:
281
- class - the SolrCache implementation LRUCache or FastLRUCache
282
- size - the maximum number of entries in the cache
283
- initialSize - the initial capacity (number of entries) of
284
- the cache. (seel java.util.HashMap)
285
- autowarmCount - the number of entries to prepopulate from
286
- and old cache.
287
- -->
288
- <filterCache class="solr.FastLRUCache" size="512" initialSize="512" autowarmCount="0"/>
289
- <!-- Cache used to hold field values that are quickly accessible
290
- by document id. The fieldValueCache is created by default
291
- even if not configured here.
292
- <fieldValueCache
293
- class="solr.FastLRUCache"
294
- size="512"
295
- autowarmCount="128"
296
- showItems="32"
297
- />
158
+ FastLRUCache, based on a ConcurrentHashMap.
159
+
160
+ FastLRUCache has faster gets and slower puts in single
161
+ threaded operation and thus is generally faster than LRUCache
162
+ when the hit ratio of the cache is high (> 75%), and may be
163
+ faster under other scenarios on multi-cpu systems.
298
164
  -->
299
- <!-- queryResultCache caches results of searches - ordered lists of
300
- document ids (DocList) based on a query, a sort, and the range
301
- of documents requested. -->
302
- <queryResultCache class="solr.LRUCache" size="512" initialSize="512" autowarmCount="0"/>
303
- <!-- documentCache caches Lucene Document objects (the stored fields for each document).
304
- Since Lucene internal document ids are transient, this cache will not be autowarmed. -->
305
- <documentCache class="solr.LRUCache" size="512" initialSize="512" autowarmCount="0"/>
306
- <!-- If true, stored fields that are not requested will be loaded lazily.
307
- This can result in a significant speed improvement if the usual case is to
308
- not load all stored fields, especially if the skipped fields are large
309
- compressed text fields.
165
+
166
+ <!-- Filter Cache
167
+
168
+ Cache used by SolrIndexSearcher for filters (DocSets),
169
+ unordered sets of *all* documents that match a query. When a
170
+ new searcher is opened, its caches may be prepopulated or
171
+ "autowarmed" using data from caches in the old searcher.
172
+ autowarmCount is the number of items to prepopulate. For
173
+ LRUCache, the autowarmed items will be the most recently
174
+ accessed items.
175
+
176
+ Parameters:
177
+ class - the SolrCache implementation LRUCache or
178
+ (LRUCache or FastLRUCache)
179
+ size - the maximum number of entries in the cache
180
+ initialSize - the initial capacity (number of entries) of
181
+ the cache. (see java.util.HashMap)
182
+ autowarmCount - the number of entries to prepopulate from
183
+ and old cache.
184
+ -->
185
+ <filterCache class="solr.FastLRUCache"
186
+ size="512"
187
+ initialSize="512"
188
+ autowarmCount="0"/>
189
+
190
+ <!-- Query Result Cache
191
+
192
+ Caches results of searches - ordered lists of document ids
193
+ (DocList) based on a query, a sort, and the range of documents requested.
194
+ -->
195
+ <queryResultCache class="solr.LRUCache"
196
+ size="512"
197
+ initialSize="512"
198
+ autowarmCount="0"/>
199
+
200
+ <!-- Document Cache
201
+
202
+ Caches Lucene Document objects (the stored fields for each
203
+ document). Since Lucene internal document ids are transient,
204
+ this cache will not be autowarmed.
205
+ -->
206
+ <documentCache class="solr.LRUCache"
207
+ size="512"
208
+ initialSize="512"
209
+ autowarmCount="0"/>
210
+
211
+ <!-- Lazy Field Loading
212
+
213
+ If true, stored fields that are not requested will be loaded
214
+ lazily. This can result in a significant speed improvement
215
+ if the usual case is to not load all stored fields,
216
+ especially if the skipped fields are large compressed text
217
+ fields.
310
218
  -->
311
219
  <enableLazyFieldLoading>true</enableLazyFieldLoading>
312
- <!-- Example of a generic cache. These caches may be accessed by name
313
- through SolrIndexSearcher.getCache(),cacheLookup(), and cacheInsert().
314
- The purpose is to enable easy caching of user/application level data.
315
- The regenerator argument should be specified as an implementation
316
- of solr.search.CacheRegenerator if autowarming is desired. -->
317
- <!--
318
- <cache name="myUserCache"
319
- class="solr.LRUCache"
320
- size="4096"
321
- initialSize="1024"
322
- autowarmCount="1024"
323
- regenerator="org.mycompany.mypackage.MyRegenerator"
324
- />
325
- -->
326
- <!-- An optimization that attempts to use a filter to satisfy a search.
327
- If the requested sort does not include score, then the filterCache
328
- will be checked for a filter matching the query. If found, the filter
329
- will be used as the source of document ids, and then the sort will be
330
- applied to that.
331
- <useFilterForSortedQuery>true</useFilterForSortedQuery>
332
- -->
333
- <!-- An optimization for use with the queryResultCache. When a search
334
- is requested, a superset of the requested number of document ids
335
- are collected. For example, if a search for a particular query
336
- requests matching documents 10 through 19, and queryWindowSize is 50,
337
- then documents 0 through 49 will be collected and cached. Any further
338
- requests in that range can be satisfied via the cache. -->
339
- <queryResultWindowSize>20</queryResultWindowSize>
340
- <!-- Maximum number of documents to cache for any entry in the
341
- queryResultCache. -->
342
- <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
343
- <!-- a newSearcher event is fired whenever a new searcher is being prepared
344
- and there is a current searcher handling requests (aka registered).
345
- It can be used to prime certain caches to prevent long request times for
346
- certain requests.
347
- -->
348
- <!-- QuerySenderListener takes an array of NamedList and executes a
349
- local query request for each NamedList in sequence. -->
350
- <listener event="newSearcher" class="solr.QuerySenderListener">
351
- <arr name="queries">
352
- <!--
353
- <lst> <str name="q">solr</str> <str name="start">0</str> <str name="rows">10</str> </lst>
354
- <lst> <str name="q">rocks</str> <str name="start">0</str> <str name="rows">10</str> </lst>
355
- <lst><str name="q">static newSearcher warming query from solrconfig.xml</str></lst>
356
- -->
357
- </arr>
358
- </listener>
359
- <!-- a firstSearcher event is fired whenever a new searcher is being
360
- prepared but there is no current registered searcher to handle
361
- requests or to gain autowarming data from. -->
362
- <listener event="firstSearcher" class="solr.QuerySenderListener">
363
- <arr name="queries">
364
- <lst>
365
- <str name="q">solr rocks</str>
366
- <str name="start">0</str>
367
- <str name="rows">10</str>
368
- </lst>
369
- <lst>
370
- <str name="q">static firstSearcher warming query from solrconfig.xml</str>
371
- </lst>
372
- </arr>
373
- </listener>
374
- <!-- If a search request comes in and there is no current registered searcher,
375
- then immediately register the still warming searcher and use it. If
376
- "false" then all requests will block until the first searcher is done
377
- warming. -->
220
+
221
+ <!-- Use Filter For Sorted Query
222
+
223
+ A possible optimization that attempts to use a filter to
224
+ satisfy a search. If the requested sort does not include
225
+ score, then the filterCache will be checked for a filter
226
+ matching the query. If found, the filter will be used as the
227
+ source of document ids, and then the sort will be applied to
228
+ that.
229
+
230
+ For most situations, this will not be useful unless you
231
+ frequently get the same search repeatedly with different sort
232
+ options, and none of them ever use "score"
233
+ -->
234
+ <!--
235
+ <useFilterForSortedQuery>true</useFilterForSortedQuery>
236
+ -->
237
+
238
+ <!-- Result Window Size
239
+
240
+ An optimization for use with the queryResultCache. When a search
241
+ is requested, a superset of the requested number of document ids
242
+ are collected. For example, if a search for a particular query
243
+ requests matching documents 10 through 19, and queryWindowSize is 50,
244
+ then documents 0 through 49 will be collected and cached. Any further
245
+ requests in that range can be satisfied via the cache.
246
+ -->
247
+ <queryResultWindowSize>20</queryResultWindowSize>
248
+
249
+ <!-- Maximum number of documents to cache for any entry in the
250
+ queryResultCache.
251
+ -->
252
+ <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
253
+
254
+ <!-- Query Related Event Listeners
255
+
256
+ Various IndexSearcher related events can trigger Listeners to
257
+ take actions.
258
+
259
+ newSearcher - fired whenever a new searcher is being prepared
260
+ and there is a current searcher handling requests (aka
261
+ registered). It can be used to prime certain caches to
262
+ prevent long request times for certain requests.
263
+
264
+ firstSearcher - fired whenever a new searcher is being
265
+ prepared but there is no current registered searcher to handle
266
+ requests or to gain autowarming data from.
267
+
268
+
269
+ -->
270
+
271
+ <!-- Use Cold Searcher
272
+
273
+ If a search request comes in and there is no current
274
+ registered searcher, then immediately register the still
275
+ warming searcher and use it. If "false" then all requests
276
+ will block until the first searcher is done warming.
277
+ -->
378
278
  <useColdSearcher>false</useColdSearcher>
379
- <!-- Maximum number of searchers that may be warming in the background
380
- concurrently. An error is returned if this limit is exceeded. Recommend
381
- 1-2 for read-only slaves, higher for masters w/o cache warming. -->
382
- <maxWarmingSearchers>2</maxWarmingSearchers>
279
+
280
+ <!-- Max Warming Searchers
281
+
282
+ Maximum number of searchers that may be warming in the
283
+ background concurrently. An error is returned if this limit
284
+ is exceeded.
285
+
286
+ Recommend values of 1-2 for read-only slaves, higher for
287
+ masters w/o cache warming.
288
+ -->
289
+ <maxWarmingSearchers>5</maxWarmingSearchers>
290
+
383
291
  </query>
384
- <!--
385
- Let the dispatch filter handler /select?qt=XXX
386
- handleSelect=true will use consistent error handling for /select and /update
387
- handleSelect=false will use solr1.1 style error formatting
388
- -->
389
- <requestDispatcher handleSelect="true">
390
- <!--Make sure your system has some authentication before enabling remote streaming! -->
391
- <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048000"/>
392
- <!-- Set HTTP caching related parameters (for proxy caches and clients).
393
-
394
- To get the behaviour of Solr 1.2 (ie: no caching related headers)
395
- use the never304="true" option and do not specify a value for
396
- <cacheControl>
397
- -->
398
- <!-- <httpCaching never304="true"> -->
399
- <httpCaching lastModifiedFrom="openTime" etagSeed="Solr">
400
- <!-- lastModFrom="openTime" is the default, the Last-Modified value
401
- (and validation against If-Modified-Since requests) will all be
402
- relative to when the current Searcher was opened.
403
- You can change it to lastModFrom="dirLastMod" if you want the
404
- value to exactly corrispond to when the physical index was last
405
- modified.
406
-
407
- etagSeed="..." is an option you can change to force the ETag
408
- header (and validation against If-None-Match requests) to be
409
- differnet even if the index has not changed (ie: when making
410
- significant changes to your config file)
411
-
412
- lastModifiedFrom and etagSeed are both ignored if you use the
413
- never304="true" option.
414
- -->
415
- <!-- If you include a <cacheControl> directive, it will be used to
416
- generate a Cache-Control header, as well as an Expires header
417
- if the value contains "max-age="
418
-
419
- By default, no Cache-Control header is generated.
420
-
421
- You can use the <cacheControl> option even if you have set
422
- never304="true"
423
- -->
424
- <!-- <cacheControl>max-age=30, public</cacheControl> -->
425
- </httpCaching>
426
- </requestDispatcher>
427
- <!-- requestHandler plugins... incoming queries will be dispatched to the
428
- correct handler based on the path or the qt (query type) param.
429
- Names starting with a '/' are accessed with the a path equal to the
430
- registered name. Names without a leading '/' are accessed with:
431
- http://host/app/select?qt=name
432
- If no qt is defined, the requestHandler that declares default="true"
433
- will be used.
434
- -->
435
- <requestHandler name="standard" class="solr.SearchHandler" default="true">
436
- <!-- default values for query parameters -->
437
- <lst name="defaults">
438
- <str name="echoParams">explicit</str>
439
- <!--
440
- <int name="rows">10</int>
441
- <str name="fl">*</str>
442
- <str name="version">2.1</str>
443
- -->
444
- </lst>
445
- </requestHandler>
446
- <!-- Please refer to http://wiki.apache.org/solr/SolrReplication for details on configuring replication -->
447
- <!-- remove the <lst name="master"> section if this is just a slave -->
448
- <!-- remove the <lst name="slave"> section if this is just a master -->
449
- <!--
450
- <requestHandler name="/replication" class="solr.ReplicationHandler" >
451
- <lst name="master">
452
- <str name="replicateAfter">commit</str>
453
- <str name="replicateAfter">startup</str>
454
- <str name="confFiles">schema.xml,stopwords.txt</str>
455
- </lst>
456
- <lst name="slave">
457
- <str name="masterUrl">http://localhost:8983/solr/replication</str>
458
- <str name="pollInterval">00:00:60</str>
459
- </lst>
460
- </requestHandler>-->
461
- <!-- DisMaxRequestHandler allows easy searching across multiple fields
462
- for simple user-entered phrases. It's implementation is now
463
- just the standard SearchHandler with a default query type
464
- of "dismax".
465
- see http://wiki.apache.org/solr/DisMaxRequestHandler
466
- -->
467
- <requestHandler name="dismax" class="solr.SearchHandler">
468
- <lst name="defaults">
469
- <str name="defType">dismax</str>
470
- <str name="echoParams">explicit</str>
471
- <float name="tie">0.01</float>
472
- <str name="qf">
473
- text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0 manu^1.1 cat^1.4
474
- </str>
475
- <str name="pf">
476
- text^0.2 features^1.1 name^1.5 manu^1.4 manu_exact^1.9
477
- </str>
478
- <str name="bf">
479
- popularity^0.5 recip(price,1,1000,1000)^0.3
480
- </str>
481
- <str name="fl">
482
- id,name,price,score
483
- </str>
484
- <str name="mm">
485
- 2&lt;-1 5&lt;-2 6&lt;90%
486
- </str>
487
- <int name="ps">100</int>
488
- <str name="q.alt">*:*</str>
489
- <!-- example highlighter config, enable per-query with hl=true -->
490
- <str name="hl.fl">text features name</str>
491
- <!-- for this field, we want no fragmenting, just highlighting -->
492
- <str name="f.name.hl.fragsize">0</str>
493
- <!-- instructs Solr to return the field itself if no query terms are
494
- found -->
495
- <str name="f.name.hl.alternateField">name</str>
496
- <str name="f.text.hl.fragmenter">regex</str>
497
- <!-- defined below -->
498
- </lst>
499
- </requestHandler>
500
- <!-- Note how you can register the same handler multiple times with
501
- different names (and different init parameters)
292
+
293
+
294
+ <!-- Request Dispatcher
295
+
296
+ This section contains instructions for how the SolrDispatchFilter
297
+ should behave when processing requests for this SolrCore.
298
+
299
+ handleSelect is a legacy option that affects the behavior of requests
300
+ such as /select?qt=XXX
301
+
302
+ handleSelect="true" will cause the SolrDispatchFilter to process
303
+ the request and dispatch the query to a handler specified by the
304
+ "qt" param, assuming "/select" isn't already registered.
305
+
306
+ handleSelect="false" will cause the SolrDispatchFilter to
307
+ ignore "/select" requests, resulting in a 404 unless a handler
308
+ is explicitly registered with the name "/select"
309
+
310
+ handleSelect="true" is not recommended for new users, but is the default
311
+ for backwards compatibility
502
312
  -->
503
- <requestHandler name="partitioned" class="solr.SearchHandler">
504
- <lst name="defaults">
505
- <str name="defType">dismax</str>
506
- <str name="echoParams">explicit</str>
507
- <str name="qf">text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0</str>
508
- <str name="mm">2&lt;-1 5&lt;-2 6&lt;90%</str>
509
- <!-- This is an example of using Date Math to specify a constantly
510
- moving date range in a config...
511
- -->
512
- <str name="bq">incubationdate_dt:[* TO NOW/DAY-1MONTH]^2.2</str>
513
- </lst>
514
- <!-- In addition to defaults, "appends" params can be specified
515
- to identify values which should be appended to the list of
516
- multi-val params from the query (or the existing "defaults").
517
-
518
- In this example, the param "fq=instock:true" will be appended to
519
- any query time fq params the user may specify, as a mechanism for
520
- partitioning the index, independent of any user selected filtering
521
- that may also be desired (perhaps as a result of faceted searching).
522
-
523
- NOTE: there is *absolutely* nothing a client can do to prevent these
524
- "appends" values from being used, so don't use this mechanism
525
- unless you are sure you always want it.
313
+ <requestDispatcher handleSelect="false" >
314
+ <!-- Request Parsing
315
+
316
+ These settings indicate how Solr Requests may be parsed, and
317
+ what restrictions may be placed on the ContentStreams from
318
+ those requests
319
+
320
+ enableRemoteStreaming - enables use of the stream.file
321
+ and stream.url parameters for specifying remote streams.
322
+
323
+ multipartUploadLimitInKB - specifies the max size (in KiB) of
324
+ Multipart File Uploads that Solr will allow in a Request.
325
+
326
+ formdataUploadLimitInKB - specifies the max size (in KiB) of
327
+ form data (application/x-www-form-urlencoded) sent via
328
+ POST. You can use POST to pass request parameters not
329
+ fitting into the URL.
330
+
331
+ *** WARNING ***
332
+ The settings below authorize Solr to fetch remote files, You
333
+ should make sure your system has some authentication before
334
+ using enableRemoteStreaming="true"
335
+
336
+ -->
337
+
338
+ <!-- HTTP Caching
339
+
340
+ Set HTTP caching related parameters (for proxy caches and clients).
341
+
342
+ The options below instruct Solr not to output any HTTP Caching
343
+ related headers
526
344
  -->
527
- <lst name="appends">
528
- <str name="fq">inStock:true</str>
529
- </lst>
530
- <!-- "invariants" are a way of letting the Solr maintainer lock down
531
- the options available to Solr clients. Any params values
532
- specified here are used regardless of what values may be specified
533
- in either the query, the "defaults", or the "appends" params.
534
-
535
- In this example, the facet.field and facet.query params are fixed,
536
- limiting the facets clients can use. Faceting is not turned on by
537
- default - but if the client does specify facet=true in the request,
538
- these are the only facets they will be able to see counts for;
539
- regardless of what other facet.field or facet.query params they
540
- may specify.
541
-
542
- NOTE: there is *absolutely* nothing a client can do to prevent these
543
- "invariants" values from being used, so don't use this mechanism
544
- unless you are sure you always want it.
345
+ <httpCaching never304="true" />
346
+ <!-- If you include a <cacheControl> directive, it will be used to
347
+ generate a Cache-Control header (as well as an Expires header
348
+ if the value contains "max-age=")
349
+
350
+ By default, no Cache-Control header is generated.
351
+
352
+ You can use the <cacheControl> option even if you have set
353
+ never304="true"
545
354
  -->
546
- <lst name="invariants">
547
- <str name="facet.field">cat</str>
548
- <str name="facet.field">manu_exact</str>
549
- <str name="facet.query">price:[* TO 500]</str>
550
- <str name="facet.query">price:[500 TO *]</str>
551
- </lst>
552
- </requestHandler>
553
- <!--
554
- Search components are registered to SolrCore and used by Search Handlers
555
-
556
- By default, the following components are avaliable:
557
-
558
- <searchComponent name="query" class="org.apache.solr.handler.component.QueryComponent" />
559
- <searchComponent name="facet" class="org.apache.solr.handler.component.FacetComponent" />
560
- <searchComponent name="mlt" class="org.apache.solr.handler.component.MoreLikeThisComponent" />
561
- <searchComponent name="highlight" class="org.apache.solr.handler.component.HighlightComponent" />
562
- <searchComponent name="stats" class="org.apache.solr.handler.component.StatsComponent" />
563
- <searchComponent name="debug" class="org.apache.solr.handler.component.DebugComponent" />
564
-
565
- Default configuration in a requestHandler would look like:
566
- <arr name="components">
567
- <str>query</str>
568
- <str>facet</str>
569
- <str>mlt</str>
570
- <str>highlight</str>
571
- <str>stats</str>
572
- <str>debug</str>
573
- </arr>
355
+ <!--
356
+ <httpCaching never304="true" >
357
+ <cacheControl>max-age=30, public</cacheControl>
358
+ </httpCaching>
359
+ -->
360
+ <!-- To enable Solr to respond with automatically generated HTTP
361
+ Caching headers, and to response to Cache Validation requests
362
+ correctly, set the value of never304="false"
363
+
364
+ This will cause Solr to generate Last-Modified and ETag
365
+ headers based on the properties of the Index.
366
+
367
+ The following options can also be specified to affect the
368
+ values of these headers...
369
+
370
+ lastModFrom - the default value is "openTime" which means the
371
+ Last-Modified value (and validation against If-Modified-Since
372
+ requests) will all be relative to when the current Searcher
373
+ was opened. You can change it to lastModFrom="dirLastMod" if
374
+ you want the value to exactly correspond to when the physical
375
+ index was last modified.
376
+
377
+ etagSeed="..." is an option you can change to force the ETag
378
+ header (and validation against If-None-Match requests) to be
379
+ different even if the index has not changed (ie: when making
380
+ significant changes to your config file)
381
+
382
+ (lastModifiedFrom and etagSeed are both ignored if you use
383
+ the never304="true" option)
384
+ -->
385
+ <!--
386
+ <httpCaching lastModifiedFrom="openTime"
387
+ etagSeed="Solr">
388
+ <cacheControl>max-age=30, public</cacheControl>
389
+ </httpCaching>
390
+ -->
391
+ </requestDispatcher>
392
+
393
+ <!-- Request Handlers
394
+
395
+ http://wiki.apache.org/solr/SolrRequestHandler
396
+
397
+ Incoming queries will be dispatched to a specific handler by name
398
+ based on the path specified in the request.
399
+
400
+ Legacy behavior: If the request path uses "/select" but no Request
401
+ Handler has that name, and if handleSelect="true" has been specified in
402
+ the requestDispatcher, then the Request Handler is dispatched based on
403
+ the qt parameter. Handlers without a leading '/' are accessed this way
404
+ like so: http://host/app/[core/]select?qt=name If no qt is
405
+ given, then the requestHandler that declares default="true" will be
406
+ used or the one named "standard".
407
+
408
+ If a Request Handler is declared with startup="lazy", then it will
409
+ not be initialized until the first request that uses it.
574
410
 
575
- If you register a searchComponent to one of the standard names, that will be used instead.
576
- To insert components before or after the 'standard' components, use:
577
-
578
- <arr name="first-components">
579
- <str>myFirstComponentName</str>
580
- </arr>
581
-
582
- <arr name="last-components">
583
- <str>myLastComponentName</str>
584
- </arr>
585
- -->
586
- <!-- The spell check component can return a list of alternative spelling
587
- suggestions. -->
588
- <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
589
- <str name="queryAnalyzerFieldType">textSpell</str>
590
- <lst name="spellchecker">
591
- <str name="name">default</str>
592
- <str name="field">name</str>
593
- <str name="spellcheckIndexDir">./spellchecker</str>
594
- </lst>
595
- <!-- a spellchecker that uses a different distance measure
596
- <lst name="spellchecker">
597
- <str name="name">jarowinkler</str>
598
- <str name="field">spell</str>
599
- <str name="distanceMeasure">org.apache.lucene.search.spell.JaroWinklerDistance</str>
600
- <str name="spellcheckIndexDir">./spellchecker2</str>
601
- </lst>
602
- -->
603
- <!-- a file based spell checker
604
- <lst name="spellchecker">
605
- <str name="classname">solr.FileBasedSpellChecker</str>
606
- <str name="name">file</str>
607
- <str name="sourceLocation">spellings.txt</str>
608
- <str name="characterEncoding">UTF-8</str>
609
- <str name="spellcheckIndexDir">./spellcheckerFile</str>
610
- </lst>
611
411
  -->
612
- </searchComponent>
613
- <!-- A request handler utilizing the spellcheck component.
614
- #############################################################################
615
- NOTE: This is purely as an example. The whole purpose of the
616
- SpellCheckComponent is to hook it into the request handler that handles (i.e.
617
- the standard or dismax SearchHandler) queries such that a separate request is
618
- not needed to get suggestions.
619
-
620
- IN OTHER WORDS, THERE IS REALLY GOOD CHANCE THE SETUP BELOW IS NOT WHAT YOU
621
- WANT FOR YOUR PRODUCTION SYSTEM!
622
- #############################################################################
623
- -->
624
- <requestHandler name="/spell" class="solr.SearchHandler" lazy="true">
625
- <lst name="defaults">
626
- <!-- omp = Only More Popular -->
627
- <str name="spellcheck.onlyMorePopular">false</str>
628
- <!-- exr = Extended Results -->
629
- <str name="spellcheck.extendedResults">false</str>
630
- <!-- The number of suggestions to return -->
631
- <str name="spellcheck.count">1</str>
632
- </lst>
412
+ <!-- SearchHandler
413
+
414
+ http://wiki.apache.org/solr/SearchHandler
415
+
416
+ For processing Search Queries, the primary Request Handler
417
+ provided with Solr is "SearchHandler" It delegates to a sequent
418
+ of SearchComponents (see below) and supports distributed
419
+ queries across multiple shards
420
+ -->
421
+ <requestHandler name="/select" class="solr.SearchHandler">
633
422
  <arr name="last-components">
634
423
  <str>spellcheck</str>
635
424
  </arr>
636
425
  </requestHandler>
637
- <searchComponent name="tvComponent" class="org.apache.solr.handler.component.TermVectorComponent"/>
638
- <!-- A Req Handler for working with the tvComponent. This is purely as an example.
639
- You will likely want to add the component to your already specified request handlers. -->
640
- <requestHandler name="tvrh" class="org.apache.solr.handler.component.SearchHandler">
641
- <lst name="defaults">
642
- <bool name="tv">true</bool>
643
- </lst>
644
- <arr name="last-components">
645
- <str>tvComponent</str>
646
- </arr>
426
+
427
+ <!-- A request handler that returns indented JSON by default -->
428
+ <requestHandler name="/query" class="solr.SearchHandler">
429
+ <lst name="defaults">
430
+ <str name="echoParams">explicit</str>
431
+ <str name="wt">json</str>
432
+ <str name="indent">true</str>
433
+ <str name="df">text</str>
434
+ </lst>
435
+ <arr name="last-components">
436
+ <str>spellcheck</str>
437
+ </arr>
647
438
  </requestHandler>
648
- <!-- Clustering Component
649
- http://wiki.apache.org/solr/ClusteringComponent
650
- This relies on third party jars which are not included in the release.
651
- To use this component (and the "/clustering" handler)
652
- Those jars will need to be downloaded, and you'll need to set the
653
- solr.cluster.enabled system property when running solr...
654
- java -Dsolr.clustering.enabled=true -jar start.jar
655
- -->
656
- <searchComponent name="clusteringComponent" enable="${solr.clustering.enabled:false}" class="org.apache.solr.handler.clustering.ClusteringComponent">
657
- <!-- Declare an engine -->
658
- <lst name="engine">
659
- <!-- The name, only one can be named "default" -->
660
- <str name="name">default</str>
661
- <!--
662
- Class name of Carrot2 clustering algorithm. Currently available algorithms are:
663
-
664
- * org.carrot2.clustering.lingo.LingoClusteringAlgorithm
665
- * org.carrot2.clustering.stc.STCClusteringAlgorithm
666
-
667
- See http://project.carrot2.org/algorithms.html for the algorithm's characteristics.
668
- -->
669
- <str name="carrot.algorithm">org.carrot2.clustering.lingo.LingoClusteringAlgorithm</str>
670
- <!--
671
- Overriding values for Carrot2 default algorithm attributes. For a description
672
- of all available attributes, see: http://download.carrot2.org/stable/manual/#chapter.components.
673
- Use attribute key as name attribute of str elements below. These can be further
674
- overridden for individual requests by specifying attribute key as request
675
- parameter name and attribute value as parameter value.
676
- -->
677
- <str name="LingoClusteringAlgorithm.desiredClusterCountBase">20</str>
678
- </lst>
679
- <lst name="engine">
680
- <str name="name">stc</str>
681
- <str name="carrot.algorithm">org.carrot2.clustering.stc.STCClusteringAlgorithm</str>
682
- </lst>
683
- </searchComponent>
684
- <requestHandler name="/clustering" enable="${solr.clustering.enabled:false}" class="solr.SearchHandler">
685
- <lst name="defaults">
686
- <bool name="clustering">true</bool>
687
- <str name="clustering.engine">default</str>
688
- <bool name="clustering.results">true</bool>
689
- <!-- The title field -->
690
- <str name="carrot.title">name</str>
691
- <str name="carrot.url">id</str>
692
- <!-- The field to cluster on -->
693
- <str name="carrot.snippet">features</str>
694
- <!-- produce summaries -->
695
- <bool name="carrot.produceSummary">true</bool>
696
- <!-- the maximum number of labels per cluster -->
697
- <!--<int name="carrot.numDescriptions">5</int>-->
698
- <!-- produce sub clusters -->
699
- <bool name="carrot.outputSubClusters">false</bool>
700
- </lst>
701
- <arr name="last-components">
702
- <str>clusteringComponent</str>
703
- </arr>
439
+
440
+
441
+ <!-- realtime get handler, guaranteed to return the latest stored fields of
442
+ any document, without the need to commit or open a new searcher. The
443
+ current implementation relies on the updateLog feature being enabled. -->
444
+ <requestHandler name="/get" class="solr.RealTimeGetHandler">
445
+ <lst name="defaults">
446
+ <str name="omitHeader">true</str>
447
+ <str name="wt">json</str>
448
+ <str name="indent">true</str>
449
+ </lst>
450
+ </requestHandler>
451
+
452
+ <requestHandler name="/update" class="solr.UpdateRequestHandler">
704
453
  </requestHandler>
705
- <!-- Solr Cell: http://wiki.apache.org/solr/ExtractingRequestHandler -->
706
- <requestHandler name="/update/extract" class="org.apache.solr.handler.extraction.ExtractingRequestHandler" startup="lazy">
454
+
455
+ <requestHandler name="/update/json" class="solr.JsonUpdateRequestHandler">
456
+ <lst name="defaults">
457
+ <str name="stream.contentType">application/json</str>
458
+ </lst>
459
+ </requestHandler>
460
+
461
+ <requestHandler name="/update/csv" class="solr.CSVRequestHandler">
462
+ <lst name="defaults">
463
+ <str name="stream.contentType">application/csv</str>
464
+ </lst>
465
+ </requestHandler>
466
+
467
+ <requestHandler name="/update/extract"
468
+ startup="lazy"
469
+ class="solr.extraction.ExtractingRequestHandler" >
707
470
  <lst name="defaults">
708
- <!-- All the main content goes into "text"... if you need to return
709
- the extracted text or do highlighting, use a stored field. -->
710
- <str name="fmap.content">text</str>
711
471
  <str name="lowernames">true</str>
712
472
  <str name="uprefix">ignored_</str>
473
+
713
474
  <!-- capture link hrefs but ignore div attributes -->
714
475
  <str name="captureAttr">true</str>
715
476
  <str name="fmap.a">links</str>
716
477
  <str name="fmap.div">ignored_</str>
717
478
  </lst>
718
479
  </requestHandler>
719
- <!-- A component to return terms and document frequency of those terms.
720
- This component does not yet support distributed search. -->
721
- <searchComponent name="termsComponent" class="org.apache.solr.handler.component.TermsComponent"/>
722
- <requestHandler name="/terms" class="org.apache.solr.handler.component.SearchHandler">
723
- <lst name="defaults">
724
- <bool name="terms">true</bool>
725
- </lst>
726
- <arr name="components">
727
- <str>termsComponent</str>
728
- </arr>
729
- </requestHandler>
730
- <!-- a search component that enables you to configure the top results for
731
- a given query regardless of the normal lucene scoring.-->
732
- <searchComponent name="elevator" class="solr.QueryElevationComponent">
733
- <!-- pick a fieldType to analyze queries -->
734
- <str name="queryFieldType">string</str>
735
- <str name="config-file">elevate.xml</str>
736
- </searchComponent>
737
- <!-- a request handler utilizing the elevator component -->
738
- <requestHandler name="/elevate" class="solr.SearchHandler" startup="lazy">
739
- <lst name="defaults">
740
- <str name="echoParams">explicit</str>
741
- </lst>
742
- <arr name="last-components">
743
- <str>elevator</str>
744
- </arr>
745
- </requestHandler>
746
- <!-- Update request handler.
747
480
 
748
- Note: Since solr1.1 requestHandlers requires a valid content type header if posted in
749
- the body. For example, curl now requires: -H 'Content-type:text/xml; charset=utf-8'
750
- The response format differs from solr1.1 formatting and returns a standard error code.
751
- To enable solr1.1 behavior, remove the /update handler or change its path
752
- -->
753
- <requestHandler name="/update" class="solr.XmlUpdateRequestHandler"/>
754
- <requestHandler name="/update/javabin" class="solr.BinaryUpdateRequestHandler"/>
755
- <!--
756
- Analysis request handler. Since Solr 1.3. Use to return how a document is analyzed. Useful
757
- for debugging and as a token server for other types of applications.
758
-
759
- This is deprecated in favor of the improved DocumentAnalysisRequestHandler and FieldAnalysisRequestHandler
760
-
761
- <requestHandler name="/analysis" class="solr.AnalysisRequestHandler" />
762
- -->
763
- <!--
764
- An analysis handler that provides a breakdown of the analysis process of provided docuemnts. This handler expects a
765
- (single) content stream with the following format:
766
-
767
- <docs>
768
- <doc>
769
- <field name="id">1</field>
770
- <field name="name">The Name</field>
771
- <field name="text">The Text Value</field>
772
- <doc>
773
- <doc>...</doc>
774
- <doc>...</doc>
775
- ...
776
- </docs>
777
-
778
- Note: Each document must contain a field which serves as the unique key. This key is used in the returned
779
- response to assoicate an analysis breakdown to the analyzed document.
780
-
781
- Like the FieldAnalysisRequestHandler, this handler also supports query analysis by
782
- sending either an "analysis.query" or "q" request paraemter that holds the query text to be analyized. It also
783
- supports the "analysis.showmatch" parameter which when set to true, all field tokens that match the query
784
- tokens will be marked as a "match".
785
- -->
786
- <requestHandler name="/analysis/document" class="solr.DocumentAnalysisRequestHandler"/>
787
- <!--
788
- RequestHandler that provides much the same functionality as analysis.jsp. Provides the ability
789
- to specify multiple field types and field names in the same request and outputs index-time and
790
- query-time analysis for each of them.
791
-
792
- Request parameters are:
793
- analysis.fieldname - The field name whose analyzers are to be used
794
- analysis.fieldtype - The field type whose analyzers are to be used
795
- analysis.fieldvalue - The text for index-time analysis
796
- q (or analysis.q) - The text for query time analysis
797
- analysis.showmatch (true|false) - When set to true and when query analysis is performed, the produced
798
- tokens of the field value analysis will be marked as "matched" for every
799
- token that is produces by the query analysis
800
- -->
801
- <requestHandler name="/analysis/field" class="solr.FieldAnalysisRequestHandler"/>
802
- <!-- CSV update handler, loaded on demand -->
803
- <requestHandler name="/update/csv" class="solr.CSVRequestHandler" startup="lazy"/>
804
- <!--
805
- Admin Handlers - This will register all the standard admin RequestHandlers. Adding
806
- this single handler is equivalent to registering:
807
-
808
- <requestHandler name="/admin/luke" class="org.apache.solr.handler.admin.LukeRequestHandler" />
809
- <requestHandler name="/admin/system" class="org.apache.solr.handler.admin.SystemInfoHandler" />
810
- <requestHandler name="/admin/plugins" class="org.apache.solr.handler.admin.PluginInfoHandler" />
811
- <requestHandler name="/admin/threads" class="org.apache.solr.handler.admin.ThreadDumpHandler" />
812
- <requestHandler name="/admin/properties" class="org.apache.solr.handler.admin.PropertiesRequestHandler" />
813
- <requestHandler name="/admin/file" class="org.apache.solr.handler.admin.ShowFileRequestHandler" >
814
-
815
- If you wish to hide files under ${solr.home}/conf, explicitly register the ShowFileRequestHandler using:
816
- <requestHandler name="/admin/file" class="org.apache.solr.handler.admin.ShowFileRequestHandler" >
481
+ <requestHandler name="/analysis/field"
482
+ startup="lazy"
483
+ class="solr.FieldAnalysisRequestHandler" />
484
+
485
+ <requestHandler name="/analysis/document"
486
+ class="solr.DocumentAnalysisRequestHandler"
487
+ startup="lazy" />
488
+
489
+ <!-- ping/healthcheck -->
490
+ <requestHandler name="/admin/ping" class="solr.PingRequestHandler">
817
491
  <lst name="invariants">
818
- <str name="hidden">synonyms.txt</str>
819
- <str name="hidden">anotherfile.txt</str>
492
+ <str name="q">solrpingquery</str>
820
493
  </lst>
821
- </requestHandler>
822
- -->
823
- <requestHandler name="/admin/" class="org.apache.solr.handler.admin.AdminHandlers"/>
824
- <!-- ping/healthcheck -->
825
- <requestHandler name="/admin/ping" class="PingRequestHandler">
826
494
  <lst name="defaults">
827
- <str name="qt">standard</str>
828
- <str name="q">solrpingquery</str>
829
495
  <str name="echoParams">all</str>
830
496
  </lst>
831
497
  </requestHandler>
832
- <!-- Echo the request contents back to the client -->
833
- <requestHandler name="/debug/dump" class="solr.DumpRequestHandler">
498
+
499
+ <requestHandler name="/debug/dump" class="solr.DumpRequestHandler" >
834
500
  <lst name="defaults">
835
- <str name="echoParams">explicit</str>
836
- <!-- for all params (including the default etc) use: 'all' -->
837
- <str name="echoHandler">true</str>
501
+ <str name="echoParams">explicit</str>
502
+ <str name="echoHandler">true</str>
838
503
  </lst>
839
504
  </requestHandler>
840
- <highlighting>
841
- <!-- Configure the standard fragmenter -->
842
- <!-- This could most likely be commented out in the "default" case -->
843
- <fragmenter name="gap" class="org.apache.solr.highlight.GapFragmenter" default="true">
844
- <lst name="defaults">
845
- <int name="hl.fragsize">100</int>
846
- </lst>
847
- </fragmenter>
848
- <!-- A regular-expression-based fragmenter (f.i., for sentence extraction) -->
849
- <fragmenter name="regex" class="org.apache.solr.highlight.RegexFragmenter">
850
- <lst name="defaults">
851
- <!-- slightly smaller fragsizes work better because of slop -->
852
- <int name="hl.fragsize">70</int>
853
- <!-- allow 50% slop on fragment sizes -->
854
- <float name="hl.regex.slop">0.5</float>
855
- <!-- a basic sentence pattern -->
856
- <str name="hl.regex.pattern">[-\w ,/\n\"']{20,200}</str>
857
- </lst>
858
- </fragmenter>
859
- <!-- Configure the standard formatter -->
860
- <formatter name="html" class="org.apache.solr.highlight.HtmlFormatter" default="true">
861
- <lst name="defaults">
862
- <str name="hl.simple.pre"><![CDATA[<em>]]></str>
863
- <str name="hl.simple.post"><![CDATA[</em>]]></str>
864
- </lst>
865
- </formatter>
866
- </highlighting>
867
- <!-- An example dedup update processor that creates the "id" field on the fly
868
- based on the hash code of some other fields. This example has overwriteDupes
869
- set to false since we are using the id field as the signatureField and Solr
870
- will maintain uniqueness based on that anyway.
871
-
872
- You have to link the chain to an update handler above to use it ie:
873
- <requestHandler name="/update "class="solr.XmlUpdateRequestHandler">
874
- <lst name="defaults">
875
- <str name="update.processor">dedupe</str>
876
- </lst>
877
- </requestHandler>
878
- -->
879
- <!--
880
- <updateRequestProcessorChain name="dedupe">
881
- <processor class="org.apache.solr.update.processor.SignatureUpdateProcessorFactory">
882
- <bool name="enabled">true</bool>
883
- <str name="signatureField">id</str>
884
- <bool name="overwriteDupes">false</bool>
885
- <str name="fields">name,features,cat</str>
886
- <str name="signatureClass">org.apache.solr.update.processor.Lookup3Signature</str>
887
- </processor>
888
- <processor class="solr.LogUpdateProcessorFactory" />
889
- <processor class="solr.RunUpdateProcessorFactory" />
890
- </updateRequestProcessorChain>
891
- -->
892
- <!-- queryResponseWriter plugins... query responses will be written using the
893
- writer specified by the 'wt' request parameter matching the name of a registered
894
- writer.
895
- The "default" writer is the default and will be used if 'wt' is not specified
896
- in the request. XMLResponseWriter will be used if nothing is specified here.
897
- The json, python, and ruby writers are also available by default.
898
-
899
- <queryResponseWriter name="xml" class="org.apache.solr.request.XMLResponseWriter" default="true"/>
900
- <queryResponseWriter name="json" class="org.apache.solr.request.JSONResponseWriter"/>
901
- <queryResponseWriter name="python" class="org.apache.solr.request.PythonResponseWriter"/>
902
- <queryResponseWriter name="ruby" class="org.apache.solr.request.RubyResponseWriter"/>
903
- <queryResponseWriter name="php" class="org.apache.solr.request.PHPResponseWriter"/>
904
- <queryResponseWriter name="phps" class="org.apache.solr.request.PHPSerializedResponseWriter"/>
905
-
906
- <queryResponseWriter name="custom" class="com.example.MyResponseWriter"/>
907
- -->
908
- <!-- XSLT response writer transforms the XML output by any xslt file found
909
- in Solr's conf/xslt directory. Changes to xslt files are checked for
910
- every xsltCacheLifetimeSeconds.
911
- -->
912
- <queryResponseWriter name="xslt" class="org.apache.solr.request.XSLTResponseWriter">
913
- <int name="xsltCacheLifetimeSeconds">5</int>
914
- </queryResponseWriter>
915
- <!-- example of registering a query parser
916
- <queryParser name="lucene" class="org.apache.solr.search.LuceneQParserPlugin"/>
917
- -->
918
- <!-- example of registering a custom function parser
919
- <valueSourceParser name="myfunc" class="com.mycompany.MyValueSourceParser" />
920
- -->
921
- <!-- config for the admin interface -->
922
- <admin>
923
- <defaultQuery>solr</defaultQuery>
924
- <!-- configure a healthcheck file for servers behind a loadbalancer
925
- <healthcheck type="file">server-enabled</healthcheck>
926
- -->
927
- </admin>
505
+
506
+ <requestHandler name="/replication" class="solr.ReplicationHandler" >
507
+ </requestHandler>
508
+
509
+ <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
510
+
511
+ <str name="queryAnalyzerFieldType">textSpell</str>
512
+
513
+ <!-- Multiple "Spell Checkers" can be declared and used by this
514
+ component
515
+ -->
516
+
517
+ <!-- a spellchecker built from a field of the main index -->
518
+ <lst name="spellchecker">
519
+ <str name="name">default</str>
520
+ <str name="field">name</str>
521
+ <str name="classname">solr.DirectSolrSpellChecker</str>
522
+ <!-- the spellcheck distance measure used, the default is the internal levenshtein -->
523
+ <str name="distanceMeasure">internal</str>
524
+ <!-- minimum accuracy needed to be considered a valid spellcheck suggestion -->
525
+ <float name="accuracy">0.5</float>
526
+ <!-- the maximum #edits we consider when enumerating terms: can be 1 or 2 -->
527
+ <int name="maxEdits">2</int>
528
+ <!-- the minimum shared prefix when enumerating terms -->
529
+ <int name="minPrefix">1</int>
530
+ <!-- maximum number of inspections per result. -->
531
+ <int name="maxInspections">5</int>
532
+ <!-- minimum length of a query term to be considered for correction -->
533
+ <int name="minQueryLength">4</int>
534
+ <!-- maximum threshold of documents a query term can appear to be considered for correction -->
535
+ <float name="maxQueryFrequency">0.01</float>
536
+ <!-- uncomment this to require suggestions to occur in 1% of the documents
537
+ <float name="thresholdTokenFrequency">.01</float>
538
+ -->
539
+ </lst>
540
+
541
+ <!-- a spellchecker that can break or combine words. See "/spell" handler below for usage -->
542
+ <lst name="spellchecker">
543
+ <str name="name">wordbreak</str>
544
+ <str name="classname">solr.WordBreakSolrSpellChecker</str>
545
+ <str name="field">name</str>
546
+ <str name="combineWords">true</str>
547
+ <str name="breakWords">true</str>
548
+ <int name="maxChanges">10</int>
549
+ </lst>
550
+ </searchComponent>
551
+
552
+ <searchComponent name="tvComponent" class="solr.TermVectorComponent"/>
553
+
554
+ <searchComponent name="terms" class="solr.TermsComponent"/>
555
+
556
+ <searchComponent class="solr.HighlightComponent" name="highlight">
557
+ <highlighting>
558
+ <!-- Configure the standard fragmenter -->
559
+ <!-- This could most likely be commented out in the "default" case -->
560
+ <fragmenter name="gap"
561
+ default="true"
562
+ class="solr.highlight.GapFragmenter">
563
+ <lst name="defaults">
564
+ <int name="hl.fragsize">100</int>
565
+ </lst>
566
+ </fragmenter>
567
+
568
+ <!-- A regular-expression-based fragmenter
569
+ (for sentence extraction)
570
+ -->
571
+ <fragmenter name="regex"
572
+ class="solr.highlight.RegexFragmenter">
573
+ <lst name="defaults">
574
+ <!-- slightly smaller fragsizes work better because of slop -->
575
+ <int name="hl.fragsize">70</int>
576
+ <!-- allow 50% slop on fragment sizes -->
577
+ <float name="hl.regex.slop">0.5</float>
578
+ <!-- a basic sentence pattern -->
579
+ <str name="hl.regex.pattern">[-\w ,/\n\&quot;&apos;]{20,200}</str>
580
+ </lst>
581
+ </fragmenter>
582
+
583
+ <!-- Configure the standard formatter -->
584
+ <formatter name="html"
585
+ default="true"
586
+ class="solr.highlight.HtmlFormatter">
587
+ <lst name="defaults">
588
+ <str name="hl.simple.pre"><![CDATA[<em>]]></str>
589
+ <str name="hl.simple.post"><![CDATA[</em>]]></str>
590
+ </lst>
591
+ </formatter>
592
+
593
+ <!-- Configure the standard encoder -->
594
+ <encoder name="html"
595
+ class="solr.highlight.HtmlEncoder" />
596
+
597
+ <!-- Configure the standard fragListBuilder -->
598
+ <fragListBuilder name="simple"
599
+ class="solr.highlight.SimpleFragListBuilder"/>
600
+
601
+ <!-- Configure the single fragListBuilder -->
602
+ <fragListBuilder name="single"
603
+ class="solr.highlight.SingleFragListBuilder"/>
604
+
605
+ <!-- Configure the weighted fragListBuilder -->
606
+ <fragListBuilder name="weighted"
607
+ default="true"
608
+ class="solr.highlight.WeightedFragListBuilder"/>
609
+
610
+ <!-- default tag FragmentsBuilder -->
611
+ <fragmentsBuilder name="default"
612
+ default="true"
613
+ class="solr.highlight.ScoreOrderFragmentsBuilder">
614
+ <!--
615
+ <lst name="defaults">
616
+ <str name="hl.multiValuedSeparatorChar">/</str>
617
+ </lst>
618
+ -->
619
+ </fragmentsBuilder>
620
+
621
+ <!-- multi-colored tag FragmentsBuilder -->
622
+ <fragmentsBuilder name="colored"
623
+ class="solr.highlight.ScoreOrderFragmentsBuilder">
624
+ <lst name="defaults">
625
+ <str name="hl.tag.pre"><![CDATA[
626
+ <b style="background:yellow">,<b style="background:lawgreen">,
627
+ <b style="background:aquamarine">,<b style="background:magenta">,
628
+ <b style="background:palegreen">,<b style="background:coral">,
629
+ <b style="background:wheat">,<b style="background:khaki">,
630
+ <b style="background:lime">,<b style="background:deepskyblue">]]></str>
631
+ <str name="hl.tag.post"><![CDATA[</b>]]></str>
632
+ </lst>
633
+ </fragmentsBuilder>
634
+
635
+ <boundaryScanner name="default"
636
+ default="true"
637
+ class="solr.highlight.SimpleBoundaryScanner">
638
+ <lst name="defaults">
639
+ <str name="hl.bs.maxScan">10</str>
640
+ <str name="hl.bs.chars">.,!? &#9;&#10;&#13;</str>
641
+ </lst>
642
+ </boundaryScanner>
643
+
644
+ <boundaryScanner name="breakIterator"
645
+ class="solr.highlight.BreakIteratorBoundaryScanner">
646
+ <lst name="defaults">
647
+ <!-- type should be one of CHARACTER, WORD(default), LINE and SENTENCE -->
648
+ <str name="hl.bs.type">WORD</str>
649
+ <!-- language and country are used when constructing Locale object. -->
650
+ <!-- And the Locale object will be used when getting instance of BreakIterator -->
651
+ <str name="hl.bs.language">en</str>
652
+ <str name="hl.bs.country">US</str>
653
+ </lst>
654
+ </boundaryScanner>
655
+ </highlighting>
656
+ </searchComponent>
657
+
928
658
  <requestHandler class="solr.MoreLikeThisHandler" name="/mlt">
929
659
  <lst name="defaults">
930
660
  <str name="mlt.mintf">1</str>
931
661
  <str name="mlt.mindf">2</str>
932
662
  </lst>
933
663
  </requestHandler>
664
+
665
+ <!-- Admin Handlers - This will register all the standard admin RequestHandlers. -->
666
+ <requestHandler name="/admin/" class="solr.admin.AdminHandlers" />
934
667
  </config>