Project

General

Profile

Download (65.8 KB) Statistics
| Branch: | Revision:

git_sitools_idoc / flarecast / data / solr / template / conf / solrconfig.xml @ master

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
  <!-- 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>4.5</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.
47

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.
53

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...
57
       
58
              <lib dir="./lib" />
59
    -->
60

    
61
  <!-- A 'dir' option by itself adds any files found in the directory 
62
       to the classpath, this is useful for including all jars in a
63
       directory.
64

65
       When a 'regex' is specified in addition to a 'dir', only the
66
       files in that directory which completely match the regex
67
       (anchored on both ends) will be included.
68

69
       If a 'dir' option (with or without a regex) is used and nothing
70
       is found that matches, a warning will be logged.
71

72
       The examples below can be used to load some solr-contribs along 
73
       with their external dependencies.
74
    -->
75
  
76
  <!-- an exact 'path' can be used instead of a 'dir' to specify a 
77
       specific jar file.  This will cause a serious error to be logged 
78
       if it can't be loaded.
79
    -->
80
  <!--
81
     <lib path="../a-jar-that-does-not-exist.jar" /> 
82
  -->
83
  
84
  <!-- Data Directory
85

86
       Used to specify an alternate directory to hold all index data
87
       other than the default ./data under the Solr home.  If
88
       replication is in use, this should match the replication
89
       configuration.
90
    -->
91
  <dataDir>${solr.data.dir:}</dataDir>
92

    
93

    
94
  <!-- The DirectoryFactory to use for indexes.
95
       
96
       solr.StandardDirectoryFactory is filesystem
97
       based and tries to pick the best implementation for the current
98
       JVM and platform.  solr.NRTCachingDirectoryFactory, the default,
99
       wraps solr.StandardDirectoryFactory and caches small files in memory
100
       for better NRT performance.
101

102
       One can force a particular implementation via solr.MMapDirectoryFactory,
103
       solr.NIOFSDirectoryFactory, or solr.SimpleFSDirectoryFactory.
104

105
       solr.RAMDirectoryFactory is memory based, not
106
       persistent, and doesn't work with replication.
107
    -->
108
  <directoryFactory name="DirectoryFactory" 
109
                    class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}"/> 
110

    
111
  <!-- The CodecFactory for defining the format of the inverted index.
112
       The default implementation is SchemaCodecFactory, which is the official Lucene
113
       index format, but hooks into the schema to provide per-field customization of
114
       the postings lists and per-document values in the fieldType element
115
       (postingsFormat/docValuesFormat). Note that most of the alternative implementations
116
       are experimental, so if you choose to customize the index format, its a good
117
       idea to convert back to the official format e.g. via IndexWriter.addIndexes(IndexReader)
118
       before upgrading to a newer version to avoid unnecessary reindexing.
119
  -->
120
  <codecFactory class="solr.SchemaCodecFactory"/>
121

    
122
  <!-- To enable dynamic schema REST APIs, use the following for <schemaFactory>:
123
  
124
       <schemaFactory class="ManagedIndexSchemaFactory">
125
         <bool name="mutable">true</bool>
126
         <str name="managedSchemaResourceName">managed-schema</str>
127
       </schemaFactory>
128
       
129
       When ManagedIndexSchemaFactory is specified, Solr will load the schema from
130
       he resource named in 'managedSchemaResourceName', rather than from schema.xml.
131
       Note that the managed schema resource CANNOT be named schema.xml.  If the managed
132
       schema does not exist, Solr will create it after reading schema.xml, then rename
133
       'schema.xml' to 'schema.xml.bak'. 
134
       
135
       Do NOT hand edit the managed schema - external modifications will be ignored and
136
       overwritten as a result of schema modification REST API calls.
137

138
       When ManagedIndexSchemaFactory is specified with mutable = true, schema
139
       modification REST API calls will be allowed; otherwise, error responses will be
140
       sent back for these requests. 
141
  -->
142
  <schemaFactory class="ClassicIndexSchemaFactory"/>
143

    
144
  <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
145
       Index Config - These settings control low-level behavior of indexing
146
       Most example settings here show the default value, but are commented
147
       out, to more easily see where customizations have been made.
148
       
149
       Note: This replaces <indexDefaults> and <mainIndex> from older versions
150
       ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
151
  <indexConfig>
152
    <!-- maxFieldLength was removed in 4.0. To get similar behavior, include a 
153
         LimitTokenCountFilterFactory in your fieldType definition. E.g. 
154
     <filter class="solr.LimitTokenCountFilterFactory" maxTokenCount="10000"/>
155
    -->
156
    <!-- Maximum time to wait for a write lock (ms) for an IndexWriter. Default: 1000 -->
157
    <!-- <writeLockTimeout>1000</writeLockTimeout>  -->
158

    
159
    <!-- The maximum number of simultaneous threads that may be
160
         indexing documents at once in IndexWriter; if more than this
161
         many threads arrive they will wait for others to finish.
162
         Default in Solr/Lucene is 8. -->
163
    <!-- <maxIndexingThreads>8</maxIndexingThreads>  -->
164

    
165
    <!-- Expert: Enabling compound file will use less files for the index, 
166
         using fewer file descriptors on the expense of performance decrease. 
167
         Default in Lucene is "true". Default in Solr is "false" (since 3.6) -->
168
    <!-- <useCompoundFile>false</useCompoundFile> -->
169

    
170
    <!-- ramBufferSizeMB sets the amount of RAM that may be used by Lucene
171
         indexing for buffering added documents and deletions before they are
172
         flushed to the Directory.
173
         maxBufferedDocs sets a limit on the number of documents buffered
174
         before flushing.
175
         If both ramBufferSizeMB and maxBufferedDocs is set, then
176
         Lucene will flush based on whichever limit is hit first.
177
         The default is 100 MB.  -->
178
    <!-- <ramBufferSizeMB>100</ramBufferSizeMB> -->
179
    <!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
180

    
181
    <!-- Expert: Merge Policy 
182
         The Merge Policy in Lucene controls how merging of segments is done.
183
         The default since Solr/Lucene 3.3 is TieredMergePolicy.
184
         The default since Lucene 2.3 was the LogByteSizeMergePolicy,
185
         Even older versions of Lucene used LogDocMergePolicy.
186
      -->
187
    <!--
188
        <mergePolicy class="org.apache.lucene.index.TieredMergePolicy">
189
          <int name="maxMergeAtOnce">10</int>
190
          <int name="segmentsPerTier">10</int>
191
        </mergePolicy>
192
      -->
193
       
194
    <!-- Merge Factor
195
         The merge factor controls how many segments will get merged at a time.
196
         For TieredMergePolicy, mergeFactor is a convenience parameter which
197
         will set both MaxMergeAtOnce and SegmentsPerTier at once.
198
         For LogByteSizeMergePolicy, mergeFactor decides how many new segments
199
         will be allowed before they are merged into one.
200
         Default is 10 for both merge policies.
201
      -->
202
    <!-- 
203
    <mergeFactor>10</mergeFactor>
204
      -->
205

    
206
    <!-- Expert: Merge Scheduler
207
         The Merge Scheduler in Lucene controls how merges are
208
         performed.  The ConcurrentMergeScheduler (Lucene 2.3 default)
209
         can perform merges in the background using separate threads.
210
         The SerialMergeScheduler (Lucene 2.2 default) does not.
211
     -->
212
    <!-- 
213
       <mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler"/>
214
       -->
215

    
216
    <!-- LockFactory 
217

218
         This option specifies which Lucene LockFactory implementation
219
         to use.
220
      
221
         single = SingleInstanceLockFactory - suggested for a
222
                  read-only index or when there is no possibility of
223
                  another process trying to modify the index.
224
         native = NativeFSLockFactory - uses OS native file locking.
225
                  Do not use when multiple solr webapps in the same
226
                  JVM are attempting to share a single index.
227
         simple = SimpleFSLockFactory  - uses a plain file for locking
228

229
         Defaults: 'native' is default for Solr3.6 and later, otherwise
230
                   'simple' is the default
231

232
         More details on the nuances of each LockFactory...
233
         http://wiki.apache.org/lucene-java/AvailableLockFactories
234
    -->
235
    <lockType>${solr.lock.type:native}</lockType>
236

    
237
    <!-- Unlock On Startup
238

239
         If true, unlock any held write or commit locks on startup.
240
         This defeats the locking mechanism that allows multiple
241
         processes to safely access a lucene index, and should be used
242
         with care. Default is "false".
243

244
         This is not needed if lock type is 'single'
245
     -->
246
    <!--
247
    <unlockOnStartup>false</unlockOnStartup>
248
      -->
249
    
250
    <!-- Expert: Controls how often Lucene loads terms into memory
251
         Default is 128 and is likely good for most everyone.
252
      -->
253
    <!-- <termIndexInterval>128</termIndexInterval> -->
254

    
255
    <!-- If true, IndexReaders will be opened/reopened from the IndexWriter
256
         instead of from the Directory. Hosts in a master/slave setup
257
         should have this set to false while those in a SolrCloud
258
         cluster need to be set to true. Default: true
259
      -->
260
    <!-- 
261
    <nrtMode>true</nrtMode>
262
      -->
263

    
264
    <!-- Commit Deletion Policy
265
         Custom deletion policies can be specified here. The class must
266
         implement org.apache.lucene.index.IndexDeletionPolicy.
267

268
         The default Solr IndexDeletionPolicy implementation supports
269
         deleting index commit points on number of commits, age of
270
         commit point and optimized status.
271
         
272
         The latest commit point should always be preserved regardless
273
         of the criteria.
274
    -->
275
    <!-- 
276
    <deletionPolicy class="solr.SolrDeletionPolicy">
277
    -->
278
      <!-- The number of commit points to be kept -->
279
      <!-- <str name="maxCommitsToKeep">1</str> -->
280
      <!-- The number of optimized commit points to be kept -->
281
      <!-- <str name="maxOptimizedCommitsToKeep">0</str> -->
282
      <!--
283
          Delete all commit points once they have reached the given age.
284
          Supports DateMathParser syntax e.g.
285
        -->
286
      <!--
287
         <str name="maxCommitAge">30MINUTES</str>
288
         <str name="maxCommitAge">1DAY</str>
289
      -->
290
    <!-- 
291
    </deletionPolicy>
292
    -->
293

    
294
    <!-- Lucene Infostream
295
       
296
         To aid in advanced debugging, Lucene provides an "InfoStream"
297
         of detailed information when indexing.
298

299
         Setting the value to true will instruct the underlying Lucene
300
         IndexWriter to write its info stream to solr's log. By default,
301
         this is enabled here, and controlled through log4j.properties.
302
      -->
303
     <infoStream>true</infoStream>
304
  </indexConfig>
305

    
306

    
307
  <!-- JMX
308
       
309
       This example enables JMX if and only if an existing MBeanServer
310
       is found, use this if you want to configure JMX through JVM
311
       parameters. Remove this to disable exposing Solr configuration
312
       and statistics to JMX.
313

314
       For more details see http://wiki.apache.org/solr/SolrJmx
315
    -->
316
  <jmx />
317
  <!-- If you want to connect to a particular server, specify the
318
       agentId 
319
    -->
320
  <!-- <jmx agentId="myAgent" /> -->
321
  <!-- If you want to start a new MBeanServer, specify the serviceUrl -->
322
  <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
323
    -->
324

    
325
  <!-- The default high-performance update handler -->
326
  <updateHandler class="solr.DirectUpdateHandler2">
327

    
328
    <!-- Enables a transaction log, used for real-time get, durability, and
329
         and solr cloud replica recovery.  The log can grow as big as
330
         uncommitted changes to the index, so use of a hard autoCommit
331
         is recommended (see below).
332
         "dir" - the target directory for transaction logs, defaults to the
333
                solr data directory.  --> 
334
    <updateLog>
335
      <str name="dir">${solr.ulog.dir:}</str>
336
    </updateLog>
337
 
338
    <!-- AutoCommit
339

340
         Perform a hard commit automatically under certain conditions.
341
         Instead of enabling autoCommit, consider using "commitWithin"
342
         when adding documents. 
343

344
         http://wiki.apache.org/solr/UpdateXmlMessages
345

346
         maxDocs - Maximum number of documents to add since the last
347
                   commit before automatically triggering a new commit.
348

349
         maxTime - Maximum amount of time in ms that is allowed to pass
350
                   since a document was added before automatically
351
                   triggering a new commit. 
352
         openSearcher - if false, the commit causes recent index changes
353
           to be flushed to stable storage, but does not cause a new
354
           searcher to be opened to make those changes visible.
355

356
         If the updateLog is enabled, then it's highly recommended to
357
         have some sort of hard autoCommit to limit the log size.
358
      -->
359
     <autoCommit> 
360
       <maxTime>${solr.autoCommit.maxTime:15000}</maxTime> 
361
       <openSearcher>false</openSearcher> 
362
     </autoCommit>
363

    
364
    <!-- softAutoCommit is like autoCommit except it causes a
365
         'soft' commit which only ensures that changes are visible
366
         but does not ensure that data is synced to disk.  This is
367
         faster and more near-realtime friendly than a hard commit.
368
      -->
369

    
370
     <autoSoftCommit> 
371
       <maxTime>${solr.autoSoftCommit.maxTime:-1}</maxTime> 
372
     </autoSoftCommit>
373

    
374
    <!-- Update Related Event Listeners
375
         
376
         Various IndexWriter related events can trigger Listeners to
377
         take actions.
378

379
         postCommit - fired after every commit or optimize command
380
         postOptimize - fired after every optimize command
381
      -->
382
    <!-- The RunExecutableListener executes an external command from a
383
         hook such as postCommit or postOptimize.
384
         
385
         exe - the name of the executable to run
386
         dir - dir to use as the current working directory. (default=".")
387
         wait - the calling thread waits until the executable returns. 
388
                (default="true")
389
         args - the arguments to pass to the program.  (default is none)
390
         env - environment variables to set.  (default is none)
391
      -->
392
    <!-- This example shows how RunExecutableListener could be used
393
         with the script based replication...
394
         http://wiki.apache.org/solr/CollectionDistribution
395
      -->
396
    <!--
397
       <listener event="postCommit" class="solr.RunExecutableListener">
398
         <str name="exe">solr/bin/snapshooter</str>
399
         <str name="dir">.</str>
400
         <bool name="wait">true</bool>
401
         <arr name="args"> <str>arg1</str> <str>arg2</str> </arr>
402
         <arr name="env"> <str>MYVAR=val1</str> </arr>
403
       </listener>
404
      -->
405

    
406
  </updateHandler>
407
  
408
  <!-- IndexReaderFactory
409

410
       Use the following format to specify a custom IndexReaderFactory,
411
       which allows for alternate IndexReader implementations.
412

413
       ** Experimental Feature **
414

415
       Please note - Using a custom IndexReaderFactory may prevent
416
       certain other features from working. The API to
417
       IndexReaderFactory may change without warning or may even be
418
       removed from future releases if the problems cannot be
419
       resolved.
420

421

422
       ** Features that may not work with custom IndexReaderFactory **
423

424
       The ReplicationHandler assumes a disk-resident index. Using a
425
       custom IndexReader implementation may cause incompatibility
426
       with ReplicationHandler and may cause replication to not work
427
       correctly. See SOLR-1366 for details.
428

429
    -->
430
  <!--
431
  <indexReaderFactory name="IndexReaderFactory" class="package.class">
432
    <str name="someArg">Some Value</str>
433
  </indexReaderFactory >
434
  -->
435
  <!-- By explicitly declaring the Factory, the termIndexDivisor can
436
       be specified.
437
    -->
438
  <!--
439
     <indexReaderFactory name="IndexReaderFactory" 
440
                         class="solr.StandardIndexReaderFactory">
441
       <int name="setTermIndexDivisor">12</int>
442
     </indexReaderFactory >
443
    -->
444

    
445
  <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
446
       Query section - these settings control query time things like caches
447
       ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
448
  <query>
449
    <!-- Max Boolean Clauses
450

451
         Maximum number of clauses in each BooleanQuery,  an exception
452
         is thrown if exceeded.
453

454
         ** WARNING **
455
         
456
         This option actually modifies a global Lucene property that
457
         will affect all SolrCores.  If multiple solrconfig.xml files
458
         disagree on this property, the value at any given moment will
459
         be based on the last SolrCore to be initialized.
460
         
461
      -->
462
    <maxBooleanClauses>1024</maxBooleanClauses>
463

    
464

    
465
    <!-- Solr Internal Query Caches
466

467
         There are two implementations of cache available for Solr,
468
         LRUCache, based on a synchronized LinkedHashMap, and
469
         FastLRUCache, based on a ConcurrentHashMap.  
470

471
         FastLRUCache has faster gets and slower puts in single
472
         threaded operation and thus is generally faster than LRUCache
473
         when the hit ratio of the cache is high (> 75%), and may be
474
         faster under other scenarios on multi-cpu systems.
475
    -->
476

    
477
    <!-- Filter Cache
478

479
         Cache used by SolrIndexSearcher for filters (DocSets),
480
         unordered sets of *all* documents that match a query.  When a
481
         new searcher is opened, its caches may be prepopulated or
482
         "autowarmed" using data from caches in the old searcher.
483
         autowarmCount is the number of items to prepopulate.  For
484
         LRUCache, the autowarmed items will be the most recently
485
         accessed items.
486

487
         Parameters:
488
           class - the SolrCache implementation LRUCache or
489
               (LRUCache or FastLRUCache)
490
           size - the maximum number of entries in the cache
491
           initialSize - the initial capacity (number of entries) of
492
               the cache.  (see java.util.HashMap)
493
           autowarmCount - the number of entries to prepopulate from
494
               and old cache.  
495
      -->
496
    <filterCache class="solr.FastLRUCache"
497
                 size="512"
498
                 initialSize="512"
499
                 autowarmCount="0"/>
500

    
501
    <!-- Query Result Cache
502
         
503
         Caches results of searches - ordered lists of document ids
504
         (DocList) based on a query, a sort, and the range of documents requested.  
505
      -->
506
    <queryResultCache class="solr.LRUCache"
507
                     size="512"
508
                     initialSize="512"
509
                     autowarmCount="0"/>
510
   
511
    <!-- Document Cache
512

513
         Caches Lucene Document objects (the stored fields for each
514
         document).  Since Lucene internal document ids are transient,
515
         this cache will not be autowarmed.  
516
      -->
517
    <documentCache class="solr.LRUCache"
518
                   size="512"
519
                   initialSize="512"
520
                   autowarmCount="0"/>
521
    
522
    <!-- custom cache currently used by block join --> 
523
    <cache name="perSegFilter"
524
      class="solr.search.LRUCache"
525
      size="10"
526
      initialSize="0"
527
      autowarmCount="10"
528
      regenerator="solr.NoOpRegenerator" />
529

    
530
    <!-- Field Value Cache
531
         
532
         Cache used to hold field values that are quickly accessible
533
         by document id.  The fieldValueCache is created by default
534
         even if not configured here.
535
      -->
536
    <!--
537
       <fieldValueCache class="solr.FastLRUCache"
538
                        size="512"
539
                        autowarmCount="128"
540
                        showItems="32" />
541
      -->
542

    
543
    <!-- Custom Cache
544

545
         Example of a generic cache.  These caches may be accessed by
546
         name through SolrIndexSearcher.getCache(),cacheLookup(), and
547
         cacheInsert().  The purpose is to enable easy caching of
548
         user/application level data.  The regenerator argument should
549
         be specified as an implementation of solr.CacheRegenerator 
550
         if autowarming is desired.  
551
      -->
552
    <!--
553
       <cache name="myUserCache"
554
              class="solr.LRUCache"
555
              size="4096"
556
              initialSize="1024"
557
              autowarmCount="1024"
558
              regenerator="com.mycompany.MyRegenerator"
559
              />
560
      -->
561

    
562

    
563
    <!-- Lazy Field Loading
564

565
         If true, stored fields that are not requested will be loaded
566
         lazily.  This can result in a significant speed improvement
567
         if the usual case is to not load all stored fields,
568
         especially if the skipped fields are large compressed text
569
         fields.
570
    -->
571
    <enableLazyFieldLoading>true</enableLazyFieldLoading>
572

    
573
   <!-- Use Filter For Sorted Query
574

575
        A possible optimization that attempts to use a filter to
576
        satisfy a search.  If the requested sort does not include
577
        score, then the filterCache will be checked for a filter
578
        matching the query. If found, the filter will be used as the
579
        source of document ids, and then the sort will be applied to
580
        that.
581

582
        For most situations, this will not be useful unless you
583
        frequently get the same search repeatedly with different sort
584
        options, and none of them ever use "score"
585
     -->
586
   <!--
587
      <useFilterForSortedQuery>true</useFilterForSortedQuery>
588
     -->
589

    
590
   <!-- Result Window Size
591

592
        An optimization for use with the queryResultCache.  When a search
593
        is requested, a superset of the requested number of document ids
594
        are collected.  For example, if a search for a particular query
595
        requests matching documents 10 through 19, and queryWindowSize is 50,
596
        then documents 0 through 49 will be collected and cached.  Any further
597
        requests in that range can be satisfied via the cache.  
598
     -->
599
   <queryResultWindowSize>20</queryResultWindowSize>
600

    
601
   <!-- Maximum number of documents to cache for any entry in the
602
        queryResultCache. 
603
     -->
604
   <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
605

    
606
   <!-- Query Related Event Listeners
607

608
        Various IndexSearcher related events can trigger Listeners to
609
        take actions.
610

611
        newSearcher - fired whenever a new searcher is being prepared
612
        and there is a current searcher handling requests (aka
613
        registered).  It can be used to prime certain caches to
614
        prevent long request times for certain requests.
615

616
        firstSearcher - fired whenever a new searcher is being
617
        prepared but there is no current registered searcher to handle
618
        requests or to gain autowarming data from.
619

620
        
621
     -->
622
    <!-- QuerySenderListener takes an array of NamedList and executes a
623
         local query request for each NamedList in sequence. 
624
      -->
625
    <listener event="newSearcher" class="solr.QuerySenderListener">
626
      <arr name="queries">
627
        <!--
628
           <lst><str name="q">solr</str><str name="sort">price asc</str></lst>
629
           <lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
630
          -->
631
      </arr>
632
    </listener>
633
    <listener event="firstSearcher" class="solr.QuerySenderListener">
634
      <arr name="queries">
635
        <lst>
636
          <str name="q">static firstSearcher warming in solrconfig.xml</str>
637
        </lst>
638
      </arr>
639
    </listener>
640

    
641
    <!-- Use Cold Searcher
642

643
         If a search request comes in and there is no current
644
         registered searcher, then immediately register the still
645
         warming searcher and use it.  If "false" then all requests
646
         will block until the first searcher is done warming.
647
      -->
648
    <useColdSearcher>false</useColdSearcher>
649

    
650
    <!-- Max Warming Searchers
651
         
652
         Maximum number of searchers that may be warming in the
653
         background concurrently.  An error is returned if this limit
654
         is exceeded.
655

656
         Recommend values of 1-2 for read-only slaves, higher for
657
         masters w/o cache warming.
658
      -->
659
    <maxWarmingSearchers>2</maxWarmingSearchers>
660

    
661
  </query>
662

    
663

    
664
  <!-- Request Dispatcher
665

666
       This section contains instructions for how the SolrDispatchFilter
667
       should behave when processing requests for this SolrCore.
668

669
       handleSelect is a legacy option that affects the behavior of requests
670
       such as /select?qt=XXX
671

672
       handleSelect="true" will cause the SolrDispatchFilter to process
673
       the request and dispatch the query to a handler specified by the 
674
       "qt" param, assuming "/select" isn't already registered.
675

676
       handleSelect="false" will cause the SolrDispatchFilter to
677
       ignore "/select" requests, resulting in a 404 unless a handler
678
       is explicitly registered with the name "/select"
679

680
       handleSelect="true" is not recommended for new users, but is the default
681
       for backwards compatibility
682
    -->
683
  <requestDispatcher handleSelect="false" >
684
    <!-- Request Parsing
685

686
         These settings indicate how Solr Requests may be parsed, and
687
         what restrictions may be placed on the ContentStreams from
688
         those requests
689

690
         enableRemoteStreaming - enables use of the stream.file
691
         and stream.url parameters for specifying remote streams.
692

693
         multipartUploadLimitInKB - specifies the max size (in KiB) of
694
         Multipart File Uploads that Solr will allow in a Request.
695
         
696
         formdataUploadLimitInKB - specifies the max size (in KiB) of
697
         form data (application/x-www-form-urlencoded) sent via
698
         POST. You can use POST to pass request parameters not
699
         fitting into the URL.
700
         
701
         addHttpRequestToContext - if set to true, it will instruct
702
         the requestParsers to include the original HttpServletRequest
703
         object in the context map of the SolrQueryRequest under the 
704
         key "httpRequest". It will not be used by any of the existing
705
         Solr components, but may be useful when developing custom 
706
         plugins.
707
         
708
         *** WARNING ***
709
         The settings below authorize Solr to fetch remote files, You
710
         should make sure your system has some authentication before
711
         using enableRemoteStreaming="true"
712

713
      --> 
714
    <requestParsers enableRemoteStreaming="true" 
715
                    multipartUploadLimitInKB="2048000"
716
                    formdataUploadLimitInKB="2048"
717
                    addHttpRequestToContext="false"/>
718

    
719
    <!-- HTTP Caching
720

721
         Set HTTP caching related parameters (for proxy caches and clients).
722

723
         The options below instruct Solr not to output any HTTP Caching
724
         related headers
725
      -->
726
    <httpCaching never304="true" />
727
    <!-- If you include a <cacheControl> directive, it will be used to
728
         generate a Cache-Control header (as well as an Expires header
729
         if the value contains "max-age=")
730
         
731
         By default, no Cache-Control header is generated.
732
         
733
         You can use the <cacheControl> option even if you have set
734
         never304="true"
735
      -->
736
    <!--
737
       <httpCaching never304="true" >
738
         <cacheControl>max-age=30, public</cacheControl> 
739
       </httpCaching>
740
      -->
741
    <!-- To enable Solr to respond with automatically generated HTTP
742
         Caching headers, and to response to Cache Validation requests
743
         correctly, set the value of never304="false"
744
         
745
         This will cause Solr to generate Last-Modified and ETag
746
         headers based on the properties of the Index.
747

748
         The following options can also be specified to affect the
749
         values of these headers...
750

751
         lastModFrom - the default value is "openTime" which means the
752
         Last-Modified value (and validation against If-Modified-Since
753
         requests) will all be relative to when the current Searcher
754
         was opened.  You can change it to lastModFrom="dirLastMod" if
755
         you want the value to exactly correspond to when the physical
756
         index was last modified.
757

758
         etagSeed="..." is an option you can change to force the ETag
759
         header (and validation against If-None-Match requests) to be
760
         different even if the index has not changed (ie: when making
761
         significant changes to your config file)
762

763
         (lastModifiedFrom and etagSeed are both ignored if you use
764
         the never304="true" option)
765
      -->
766
    <!--
767
       <httpCaching lastModifiedFrom="openTime"
768
                    etagSeed="Solr">
769
         <cacheControl>max-age=30, public</cacheControl> 
770
       </httpCaching>
771
      -->
772
  </requestDispatcher>
773

    
774
  <!-- Request Handlers 
775

776
       http://wiki.apache.org/solr/SolrRequestHandler
777

778
       Incoming queries will be dispatched to a specific handler by name
779
       based on the path specified in the request.
780

781
       Legacy behavior: If the request path uses "/select" but no Request
782
       Handler has that name, and if handleSelect="true" has been specified in
783
       the requestDispatcher, then the Request Handler is dispatched based on
784
       the qt parameter.  Handlers without a leading '/' are accessed this way
785
       like so: http://host/app/[core/]select?qt=name  If no qt is
786
       given, then the requestHandler that declares default="true" will be
787
       used or the one named "standard".
788

789
       If a Request Handler is declared with startup="lazy", then it will
790
       not be initialized until the first request that uses it.
791

792
    -->
793
  <!-- SearchHandler
794

795
       http://wiki.apache.org/solr/SearchHandler
796

797
       For processing Search Queries, the primary Request Handler
798
       provided with Solr is "SearchHandler" It delegates to a sequent
799
       of SearchComponents (see below) and supports distributed
800
       queries across multiple shards
801
    -->
802
  <requestHandler name="/select" class="solr.SearchHandler">
803
    <!-- default values for query parameters can be specified, these
804
         will be overridden by parameters in the request
805
      -->
806
     <lst name="defaults">
807
       <str name="echoParams">explicit</str>
808
       <int name="rows">10</int>       
809
     </lst>
810
    <!-- In addition to defaults, "appends" params can be specified
811
         to identify values which should be appended to the list of
812
         multi-val params from the query (or the existing "defaults").
813
      -->
814
    <!-- In this example, the param "fq=instock:true" would be appended to
815
         any query time fq params the user may specify, as a mechanism for
816
         partitioning the index, independent of any user selected filtering
817
         that may also be desired (perhaps as a result of faceted searching).
818

819
         NOTE: there is *absolutely* nothing a client can do to prevent these
820
         "appends" values from being used, so don't use this mechanism
821
         unless you are sure you always want it.
822
      -->
823
    <!--
824
       <lst name="appends">
825
         <str name="fq">inStock:true</str>
826
       </lst>
827
      -->
828
    <!-- "invariants" are a way of letting the Solr maintainer lock down
829
         the options available to Solr clients.  Any params values
830
         specified here are used regardless of what values may be specified
831
         in either the query, the "defaults", or the "appends" params.
832

833
         In this example, the facet.field and facet.query params would
834
         be fixed, limiting the facets clients can use.  Faceting is
835
         not turned on by default - but if the client does specify
836
         facet=true in the request, these are the only facets they
837
         will be able to see counts for; regardless of what other
838
         facet.field or facet.query params they may specify.
839

840
         NOTE: there is *absolutely* nothing a client can do to prevent these
841
         "invariants" values from being used, so don't use this mechanism
842
         unless you are sure you always want it.
843
      -->
844
    <!--
845
       <lst name="invariants">
846
         <str name="facet.field">cat</str>
847
         <str name="facet.field">manu_exact</str>
848
         <str name="facet.query">price:[* TO 500]</str>
849
         <str name="facet.query">price:[500 TO *]</str>
850
       </lst>
851
      -->
852
    <!-- If the default list of SearchComponents is not desired, that
853
         list can either be overridden completely, or components can be
854
         prepended or appended to the default list.  (see below)
855
      -->
856
    <!--
857
       <arr name="components">
858
         <str>nameOfCustomComponent1</str>
859
         <str>nameOfCustomComponent2</str>
860
       </arr>
861
      -->
862
    </requestHandler>
863

    
864
  <!-- A request handler that returns indented JSON by default -->
865
  <requestHandler name="/query" class="solr.SearchHandler">
866
     <lst name="defaults">
867
       <str name="echoParams">explicit</str>
868
       <str name="wt">json</str>
869
       <str name="indent">true</str>
870
       
871
     </lst>
872
  </requestHandler>
873

    
874

    
875
  <!-- realtime get handler, guaranteed to return the latest stored fields of
876
       any document, without the need to commit or open a new searcher.  The
877
       current implementation relies on the updateLog feature being enabled. -->
878
  <requestHandler name="/get" class="solr.RealTimeGetHandler">
879
     <lst name="defaults">
880
       <str name="omitHeader">true</str>
881
       <str name="wt">json</str>
882
       <str name="indent">true</str>
883
     </lst>
884
  </requestHandler>
885

    
886
 
887
  <!-- A Robust Example 
888
       
889
       This example SearchHandler declaration shows off usage of the
890
       SearchHandler with many defaults declared
891

892
       Note that multiple instances of the same Request Handler
893
       (SearchHandler) can be registered multiple times with different
894
       names (and different init parameters)
895
    -->
896
  <requestHandler name="/browse" class="solr.SearchHandler">
897
     <lst name="defaults">
898
       <str name="echoParams">explicit</str>
899

    
900
       <!-- VelocityResponseWriter settings -->
901
       <str name="wt">velocity</str>
902
       <str name="v.template">browse</str>
903
       <str name="v.layout">layout</str>
904
       <str name="title">Solritas</str>
905

    
906
       <!-- Query settings -->
907
       <str name="defType">edismax</str>
908
       <str name="qf">
909
          text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0 manu^1.1 cat^1.4
910
          title^10.0 description^5.0 keywords^5.0 author^2.0 resourcename^1.0
911
       </str>
912
       
913
       <str name="mm">100%</str>
914
       <str name="q.alt">*:*</str>
915
       <str name="rows">10</str>
916
       <str name="fl">*,score</str>
917

    
918
       <str name="mlt.qf">
919
         text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0 manu^1.1 cat^1.4
920
         title^10.0 description^5.0 keywords^5.0 author^2.0 resourcename^1.0
921
       </str>
922
       <str name="mlt.fl">text,features,name,sku,id,manu,cat,title,description,keywords,author,resourcename</str>
923
       <int name="mlt.count">3</int>
924

    
925
       <!-- Faceting defaults -->
926
       <str name="facet">on</str>
927
       <str name="facet.field">cat</str>
928
       <str name="facet.field">manu_exact</str>
929
       <str name="facet.field">content_type</str>
930
       <str name="facet.field">author_s</str>
931
       <str name="facet.query">ipod</str>
932
       <str name="facet.query">GB</str>
933
       <str name="facet.mincount">1</str>
934
       <str name="facet.pivot">cat,inStock</str>
935
       <str name="facet.range.other">after</str>
936
       <str name="facet.range">price</str>
937
       <int name="f.price.facet.range.start">0</int>
938
       <int name="f.price.facet.range.end">600</int>
939
       <int name="f.price.facet.range.gap">50</int>
940
       <str name="facet.range">popularity</str>
941
       <int name="f.popularity.facet.range.start">0</int>
942
       <int name="f.popularity.facet.range.end">10</int>
943
       <int name="f.popularity.facet.range.gap">3</int>
944
       <str name="facet.range">manufacturedate_dt</str>
945
       <str name="f.manufacturedate_dt.facet.range.start">NOW/YEAR-10YEARS</str>
946
       <str name="f.manufacturedate_dt.facet.range.end">NOW</str>
947
       <str name="f.manufacturedate_dt.facet.range.gap">+1YEAR</str>
948
       <str name="f.manufacturedate_dt.facet.range.other">before</str>
949
       <str name="f.manufacturedate_dt.facet.range.other">after</str>
950

    
951
       <!-- Highlighting defaults -->
952
       <str name="hl">on</str>
953
       <str name="hl.fl">content features title name</str>
954
       <str name="hl.encoder">html</str>
955
       <str name="hl.simple.pre">&lt;b&gt;</str>
956
       <str name="hl.simple.post">&lt;/b&gt;</str>
957
       <str name="f.title.hl.fragsize">0</str>
958
       <str name="f.title.hl.alternateField">title</str>
959
       <str name="f.name.hl.fragsize">0</str>
960
       <str name="f.name.hl.alternateField">name</str>
961
       <str name="f.content.hl.snippets">3</str>
962
       <str name="f.content.hl.fragsize">200</str>
963
       <str name="f.content.hl.alternateField">content</str>
964
       <str name="f.content.hl.maxAlternateFieldLength">750</str>
965

    
966
       <!-- Spell checking defaults -->
967
       <str name="spellcheck">on</str>
968
       <str name="spellcheck.extendedResults">false</str>       
969
       <str name="spellcheck.count">5</str>
970
       <str name="spellcheck.alternativeTermCount">2</str>
971
       <str name="spellcheck.maxResultsForSuggest">5</str>       
972
       <str name="spellcheck.collate">true</str>
973
       <str name="spellcheck.collateExtendedResults">true</str>  
974
       <str name="spellcheck.maxCollationTries">5</str>
975
       <str name="spellcheck.maxCollations">3</str>           
976
     </lst>
977

    
978
     <!-- append spellchecking to our list of components -->
979
     <arr name="last-components">
980
       <str>spellcheck</str>
981
     </arr>
982
  </requestHandler>
983

    
984

    
985
  <!-- Update Request Handler.  
986
       
987
       http://wiki.apache.org/solr/UpdateXmlMessages
988

989
       The canonical Request Handler for Modifying the Index through
990
       commands specified using XML, JSON, CSV, or JAVABIN
991

992
       Note: Since solr1.1 requestHandlers requires a valid content
993
       type header if posted in the body. For example, curl now
994
       requires: -H 'Content-type:text/xml; charset=utf-8'
995
       
996
       To override the request content type and force a specific 
997
       Content-type, use the request parameter: 
998
         ?update.contentType=text/csv
999
       
1000
       This handler will pick a response format to match the input
1001
       if the 'wt' parameter is not explicit
1002
    -->
1003
  <requestHandler name="/update" class="solr.UpdateRequestHandler">
1004
    <!-- See below for information on defining 
1005
         updateRequestProcessorChains that can be used by name 
1006
         on each Update Request
1007
      -->
1008
    <!--
1009
       <lst name="defaults">
1010
         <str name="update.chain">dedupe</str>
1011
       </lst>
1012
       -->
1013
  </requestHandler>
1014
  
1015
  
1016
  <requestHandler name="/dataimport" class="org.apache.solr.handler.dataimport.DataImportHandler">
1017
    <lst name="defaults">
1018
            <str name="config">data-config.xml</str>
1019
    </lst>
1020
  </requestHandler>
1021

    
1022
  <!-- for back compat with clients using /update/json and /update/csv -->  
1023
  <requestHandler name="/update/json" class="solr.JsonUpdateRequestHandler">
1024
        <lst name="defaults">
1025
         <str name="stream.contentType">application/json</str>
1026
       </lst>
1027
  </requestHandler>
1028
  <requestHandler name="/update/csv" class="solr.CSVRequestHandler">
1029
        <lst name="defaults">
1030
         <str name="stream.contentType">application/csv</str>
1031
       </lst>
1032
  </requestHandler>
1033

    
1034
  <!-- Solr Cell Update Request Handler
1035

1036
       http://wiki.apache.org/solr/ExtractingRequestHandler 
1037

1038
    -->
1039
  <requestHandler name="/update/extract" 
1040
                  startup="lazy"
1041
                  class="solr.extraction.ExtractingRequestHandler" >
1042
    <lst name="defaults">
1043
      <str name="lowernames">true</str>
1044
      <str name="uprefix">ignored_</str>
1045

    
1046
      <!-- capture link hrefs but ignore div attributes -->
1047
      <str name="captureAttr">true</str>
1048
      <str name="fmap.a">links</str>
1049
      <str name="fmap.div">ignored_</str>
1050
    </lst>
1051
  </requestHandler>
1052

    
1053

    
1054
  <!-- Field Analysis Request Handler
1055

1056
       RequestHandler that provides much the same functionality as
1057
       analysis.jsp. Provides the ability to specify multiple field
1058
       types and field names in the same request and outputs
1059
       index-time and query-time analysis for each of them.
1060

1061
       Request parameters are:
1062
       analysis.fieldname - field name whose analyzers are to be used
1063

1064
       analysis.fieldtype - field type whose analyzers are to be used
1065
       analysis.fieldvalue - text for index-time analysis
1066
       q (or analysis.q) - text for query time analysis
1067
       analysis.showmatch (true|false) - When set to true and when
1068
           query analysis is performed, the produced tokens of the
1069
           field value analysis will be marked as "matched" for every
1070
           token that is produces by the query analysis
1071
   -->
1072
  <requestHandler name="/analysis/field" 
1073
                  startup="lazy"
1074
                  class="solr.FieldAnalysisRequestHandler" />
1075

    
1076

    
1077
  <!-- Document Analysis Handler
1078

1079
       http://wiki.apache.org/solr/AnalysisRequestHandler
1080

1081
       An analysis handler that provides a breakdown of the analysis
1082
       process of provided documents. This handler expects a (single)
1083
       content stream with the following format:
1084

1085
       <docs>
1086
         <doc>
1087
           <field name="id">1</field>
1088
           <field name="name">The Name</field>
1089
           <field name="text">The Text Value</field>
1090
         </doc>
1091
         <doc>...</doc>
1092
         <doc>...</doc>
1093
         ...
1094
       </docs>
1095

1096
    Note: Each document must contain a field which serves as the
1097
    unique key. This key is used in the returned response to associate
1098
    an analysis breakdown to the analyzed document.
1099

1100
    Like the FieldAnalysisRequestHandler, this handler also supports
1101
    query analysis by sending either an "analysis.query" or "q"
1102
    request parameter that holds the query text to be analyzed. It
1103
    also supports the "analysis.showmatch" parameter which when set to
1104
    true, all field tokens that match the query tokens will be marked
1105
    as a "match". 
1106
  -->
1107
  <requestHandler name="/analysis/document" 
1108
                  class="solr.DocumentAnalysisRequestHandler" 
1109
                  startup="lazy" />
1110

    
1111
  <!-- Admin Handlers
1112

1113
       Admin Handlers - This will register all the standard admin
1114
       RequestHandlers.  
1115
    -->
1116
  <requestHandler name="/admin/" 
1117
                  class="solr.admin.AdminHandlers" />
1118
  <!-- This single handler is equivalent to the following... -->
1119
  <!--
1120
     <requestHandler name="/admin/luke"       class="solr.admin.LukeRequestHandler" />
1121
     <requestHandler name="/admin/system"     class="solr.admin.SystemInfoHandler" />
1122
     <requestHandler name="/admin/plugins"    class="solr.admin.PluginInfoHandler" />
1123
     <requestHandler name="/admin/threads"    class="solr.admin.ThreadDumpHandler" />
1124
     <requestHandler name="/admin/properties" class="solr.admin.PropertiesRequestHandler" />
1125
     <requestHandler name="/admin/file"       class="solr.admin.ShowFileRequestHandler" >
1126
    -->
1127
  <!-- If you wish to hide files under ${solr.home}/conf, explicitly
1128
       register the ShowFileRequestHandler using: 
1129
    -->
1130
  <!--
1131
     <requestHandler name="/admin/file" 
1132
                     class="solr.admin.ShowFileRequestHandler" >
1133
       <lst name="invariants">
1134
         <str name="hidden">synonyms.txt</str> 
1135
         <str name="hidden">anotherfile.txt</str> 
1136
       </lst>
1137
     </requestHandler>
1138
    -->
1139

    
1140
  <!-- ping/healthcheck -->
1141
  <requestHandler name="/admin/ping" class="solr.PingRequestHandler">
1142
    <lst name="invariants">
1143
      <str name="q">solrpingquery</str>
1144
    </lst>
1145
    <lst name="defaults">
1146
      <str name="echoParams">all</str>
1147
    </lst>
1148
    <!-- An optional feature of the PingRequestHandler is to configure the 
1149
         handler with a "healthcheckFile" which can be used to enable/disable 
1150
         the PingRequestHandler.
1151
         relative paths are resolved against the data dir 
1152
      -->
1153
    <!-- <str name="healthcheckFile">server-enabled.txt</str> -->
1154
  </requestHandler>
1155

    
1156
  <!-- Echo the request contents back to the client -->
1157
  <requestHandler name="/debug/dump" class="solr.DumpRequestHandler" >
1158
    <lst name="defaults">
1159
     <str name="echoParams">explicit</str> 
1160
     <str name="echoHandler">true</str>
1161
    </lst>
1162
  </requestHandler>
1163
  
1164
  <!-- Solr Replication
1165

1166
       The SolrReplicationHandler supports replicating indexes from a
1167
       "master" used for indexing and "slaves" used for queries.
1168

1169
       http://wiki.apache.org/solr/SolrReplication 
1170

1171
       It is also necessary for SolrCloud to function (in Cloud mode, the
1172
       replication handler is used to bulk transfer segments when nodes 
1173
       are added or need to recover).
1174

1175
       https://wiki.apache.org/solr/SolrCloud/
1176
    -->
1177
  <requestHandler name="/replication" class="solr.ReplicationHandler" > 
1178
    <!--
1179
       To enable simple master/slave replication, uncomment one of the 
1180
       sections below, depending on whether this solr instance should be
1181
       the "master" or a "slave".  If this instance is a "slave" you will 
1182
       also need to fill in the masterUrl to point to a real machine.
1183
    -->
1184
    <!--
1185
       <lst name="master">
1186
         <str name="replicateAfter">commit</str>
1187
         <str name="replicateAfter">startup</str>
1188
         <str name="confFiles">schema.xml,stopwords.txt</str>
1189
       </lst>
1190
    -->
1191
    <!--
1192
       <lst name="slave">
1193
         <str name="masterUrl">http://your-master-hostname:8983/solr</str>
1194
         <str name="pollInterval">00:00:60</str>
1195
       </lst>
1196
    -->
1197
  </requestHandler>
1198

    
1199
  <!-- Search Components
1200

1201
       Search components are registered to SolrCore and used by 
1202
       instances of SearchHandler (which can access them by name)
1203
       
1204
       By default, the following components are available:
1205
       
1206
       <searchComponent name="query"     class="solr.QueryComponent" />
1207
       <searchComponent name="facet"     class="solr.FacetComponent" />
1208
       <searchComponent name="mlt"       class="solr.MoreLikeThisComponent" />
1209
       <searchComponent name="highlight" class="solr.HighlightComponent" />
1210
       <searchComponent name="stats"     class="solr.StatsComponent" />
1211
       <searchComponent name="debug"     class="solr.DebugComponent" />
1212
   
1213
       Default configuration in a requestHandler would look like:
1214

1215
       <arr name="components">
1216
         <str>query</str>
1217
         <str>facet</str>
1218
         <str>mlt</str>
1219
         <str>highlight</str>
1220
         <str>stats</str>
1221
         <str>debug</str>
1222
       </arr>
1223

1224
       If you register a searchComponent to one of the standard names, 
1225
       that will be used instead of the default.
1226

1227
       To insert components before or after the 'standard' components, use:
1228
    
1229
       <arr name="first-components">
1230
         <str>myFirstComponentName</str>
1231
       </arr>
1232
    
1233
       <arr name="last-components">
1234
         <str>myLastComponentName</str>
1235
       </arr>
1236

1237
       NOTE: The component registered with the name "debug" will
1238
       always be executed after the "last-components" 
1239
       
1240
     -->
1241
  
1242
   <!-- Spell Check
1243

1244
        The spell check component can return a list of alternative spelling
1245
        suggestions.  
1246

1247
        http://wiki.apache.org/solr/SpellCheckComponent
1248
     -->
1249
  <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
1250

    
1251
    <str name="queryAnalyzerFieldType">text_general</str>
1252

    
1253
    <!-- Multiple "Spell Checkers" can be declared and used by this
1254
         component
1255
      -->
1256

    
1257
    <!-- a spellchecker built from a field of the main index -->
1258
    <lst name="spellchecker">
1259
      <str name="name">default</str>
1260
      <str name="field">text</str>
1261
      <str name="classname">solr.DirectSolrSpellChecker</str>
1262
      <!-- the spellcheck distance measure used, the default is the internal levenshtein -->
1263
      <str name="distanceMeasure">internal</str>
1264
      <!-- minimum accuracy needed to be considered a valid spellcheck suggestion -->
1265
      <float name="accuracy">0.5</float>
1266
      <!-- the maximum #edits we consider when enumerating terms: can be 1 or 2 -->
1267
      <int name="maxEdits">2</int>
1268
      <!-- the minimum shared prefix when enumerating terms -->
1269
      <int name="minPrefix">1</int>
1270
      <!-- maximum number of inspections per result. -->
1271
      <int name="maxInspections">5</int>
1272
      <!-- minimum length of a query term to be considered for correction -->
1273
      <int name="minQueryLength">4</int>
1274
      <!-- maximum threshold of documents a query term can appear to be considered for correction -->
1275
      <float name="maxQueryFrequency">0.01</float>
1276
      <!-- uncomment this to require suggestions to occur in 1% of the documents
1277
              <float name="thresholdTokenFrequency">.01</float>
1278
      -->
1279
    </lst>
1280
    
1281
    <!-- a spellchecker that can break or combine words.  See "/spell" handler below for usage -->
1282
    <lst name="spellchecker">
1283
      <str name="name">wordbreak</str>
1284
      <str name="classname">solr.WordBreakSolrSpellChecker</str>      
1285
      <str name="field">name</str>
1286
      <str name="combineWords">true</str>
1287
      <str name="breakWords">true</str>
1288
      <int name="maxChanges">10</int>
1289
    </lst>
1290

    
1291
    <!-- a spellchecker that uses a different distance measure -->
1292
    <!--
1293
       <lst name="spellchecker">
1294
         <str name="name">jarowinkler</str>
1295
         <str name="field">spell</str>
1296
         <str name="classname">solr.DirectSolrSpellChecker</str>
1297
         <str name="distanceMeasure">
1298
           org.apache.lucene.search.spell.JaroWinklerDistance
1299
         </str>
1300
       </lst>
1301
     -->
1302

    
1303
    <!-- a spellchecker that use an alternate comparator 
1304

1305
         comparatorClass be one of:
1306
          1. score (default)
1307
          2. freq (Frequency first, then score)
1308
          3. A fully qualified class name
1309
      -->
1310
    <!--
1311
       <lst name="spellchecker">
1312
         <str name="name">freq</str>
1313
         <str name="field">lowerfilt</str>
1314
         <str name="classname">solr.DirectSolrSpellChecker</str>
1315
         <str name="comparatorClass">freq</str>
1316
      -->
1317

    
1318
    <!-- A spellchecker that reads the list of words from a file -->
1319
    <!--
1320
       <lst name="spellchecker">
1321
         <str name="classname">solr.FileBasedSpellChecker</str>
1322
         <str name="name">file</str>
1323
         <str name="sourceLocation">spellings.txt</str>
1324
         <str name="characterEncoding">UTF-8</str>
1325
         <str name="spellcheckIndexDir">spellcheckerFile</str>
1326
       </lst>
1327
      -->
1328
  </searchComponent>
1329

    
1330
  <!-- A request handler for demonstrating the spellcheck component.  
1331

1332
       NOTE: This is purely as an example.  The whole purpose of the
1333
       SpellCheckComponent is to hook it into the request handler that
1334
       handles your normal user queries so that a separate request is
1335
       not needed to get suggestions.
1336

1337
       IN OTHER WORDS, THERE IS REALLY GOOD CHANCE THE SETUP BELOW IS
1338
       NOT WHAT YOU WANT FOR YOUR PRODUCTION SYSTEM!
1339
       
1340
       See http://wiki.apache.org/solr/SpellCheckComponent for details
1341
       on the request parameters.
1342
    -->
1343
  <requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
1344
    <lst name="defaults">
1345
      
1346
      <!-- Solr will use suggestions from both the 'default' spellchecker
1347
           and from the 'wordbreak' spellchecker and combine them.
1348
           collations (re-written queries) can include a combination of
1349
           corrections from both spellcheckers -->
1350
      <str name="spellcheck.dictionary">default</str>
1351
      <str name="spellcheck.dictionary">wordbreak</str>
1352
      <str name="spellcheck">on</str>
1353
      <str name="spellcheck.extendedResults">true</str>       
1354
      <str name="spellcheck.count">10</str>
1355
      <str name="spellcheck.alternativeTermCount">5</str>
1356
      <str name="spellcheck.maxResultsForSuggest">5</str>       
1357
      <str name="spellcheck.collate">true</str>
1358
      <str name="spellcheck.collateExtendedResults">true</str>  
1359
      <str name="spellcheck.maxCollationTries">10</str>
1360
      <str name="spellcheck.maxCollations">5</str>         
1361
    </lst>
1362
    <arr name="last-components">
1363
      <str>spellcheck</str>
1364
    </arr>
1365
  </requestHandler>
1366

    
1367
  <!-- Term Vector Component
1368

1369
       http://wiki.apache.org/solr/TermVectorComponent
1370
    -->
1371
  <searchComponent name="tvComponent" class="solr.TermVectorComponent"/>
1372

    
1373
  <!-- A request handler for demonstrating the term vector component
1374

1375
       This is purely as an example.
1376

1377
       In reality you will likely want to add the component to your 
1378
       already specified request handlers. 
1379
    -->
1380
  <requestHandler name="/tvrh" class="solr.SearchHandler" startup="lazy">
1381
    <lst name="defaults">
1382
      
1383
      <bool name="tv">true</bool>
1384
    </lst>
1385
    <arr name="last-components">
1386
      <str>tvComponent</str>
1387
    </arr>
1388
  </requestHandler>
1389

    
1390
  <!-- Clustering Component
1391

1392
       http://wiki.apache.org/solr/ClusteringComponent
1393
       http://carrot2.github.io/solr-integration-strategies/
1394
    -->
1395
  
1396

    
1397
  
1398
  
1399
  <!-- Terms Component
1400

1401
       http://wiki.apache.org/solr/TermsComponent
1402

1403
       A component to return terms and document frequency of those
1404
       terms
1405
    -->
1406
  <searchComponent name="terms" class="solr.TermsComponent"/>
1407

    
1408
  <!-- A request handler for demonstrating the terms component -->
1409
  <requestHandler name="/js" class="org.apache.solr.handler.js.JavaScriptRequestHandler" startup="lazy"/>
1410
  <requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
1411
     <lst name="defaults">
1412
      <bool name="terms">true</bool>
1413
      <bool name="distrib">false</bool>
1414
    </lst>     
1415
    <arr name="components">
1416
      <str>terms</str>
1417
    </arr>
1418
  </requestHandler>
1419

    
1420

    
1421
  <!-- Query Elevation Component
1422

1423
       http://wiki.apache.org/solr/QueryElevationComponent
1424

1425
       a search component that enables you to configure the top
1426
       results for a given query regardless of the normal lucene
1427
       scoring.
1428
    -->
1429
  <searchComponent name="elevator" class="solr.QueryElevationComponent" >
1430
    <!-- pick a fieldType to analyze queries -->
1431
    <str name="queryFieldType">string</str>
1432
    <str name="config-file">elevate.xml</str>
1433
  </searchComponent>
1434

    
1435
  <!-- A request handler for demonstrating the elevator component -->
1436
  <requestHandler name="/elevate" class="solr.SearchHandler" startup="lazy">
1437
    <lst name="defaults">
1438
      <str name="echoParams">explicit</str>
1439
      
1440
    </lst>
1441
    <arr name="last-components">
1442
      <str>elevator</str>
1443
    </arr>
1444
  </requestHandler>
1445

    
1446
  <!-- Highlighting Component
1447

1448
       http://wiki.apache.org/solr/HighlightingParameters
1449
    -->
1450
  <searchComponent class="solr.HighlightComponent" name="highlight">
1451
    <highlighting>
1452
      <!-- Configure the standard fragmenter -->
1453
      <!-- This could most likely be commented out in the "default" case -->
1454
      <fragmenter name="gap" 
1455
                  default="true"
1456
                  class="solr.highlight.GapFragmenter">
1457
        <lst name="defaults">
1458
          <int name="hl.fragsize">100</int>
1459
        </lst>
1460
      </fragmenter>
1461

    
1462
      <!-- A regular-expression-based fragmenter 
1463
           (for sentence extraction) 
1464
        -->
1465
      <fragmenter name="regex" 
1466
                  class="solr.highlight.RegexFragmenter">
1467
        <lst name="defaults">
1468
          <!-- slightly smaller fragsizes work better because of slop -->
1469
          <int name="hl.fragsize">70</int>
1470
          <!-- allow 50% slop on fragment sizes -->
1471
          <float name="hl.regex.slop">0.5</float>
1472
          <!-- a basic sentence pattern -->
1473
          <str name="hl.regex.pattern">[-\w ,/\n\&quot;&apos;]{20,200}</str>
1474
        </lst>
1475
      </fragmenter>
1476

    
1477
      <!-- Configure the standard formatter -->
1478
      <formatter name="html" 
1479
                 default="true"
1480
                 class="solr.highlight.HtmlFormatter">
1481
        <lst name="defaults">
1482
          <str name="hl.simple.pre"><![CDATA[<em>]]></str>
1483
          <str name="hl.simple.post"><![CDATA[</em>]]></str>
1484
        </lst>
1485
      </formatter>
1486

    
1487
      <!-- Configure the standard encoder -->
1488
      <encoder name="html" 
1489
               class="solr.highlight.HtmlEncoder" />
1490

    
1491
      <!-- Configure the standard fragListBuilder -->
1492
      <fragListBuilder name="simple" 
1493
                       class="solr.highlight.SimpleFragListBuilder"/>
1494
      
1495
      <!-- Configure the single fragListBuilder -->
1496
      <fragListBuilder name="single" 
1497
                       class="solr.highlight.SingleFragListBuilder"/>
1498
      
1499
      <!-- Configure the weighted fragListBuilder -->
1500
      <fragListBuilder name="weighted" 
1501
                       default="true"
1502
                       class="solr.highlight.WeightedFragListBuilder"/>
1503
      
1504
      <!-- default tag FragmentsBuilder -->
1505
      <fragmentsBuilder name="default" 
1506
                        default="true"
1507
                        class="solr.highlight.ScoreOrderFragmentsBuilder">
1508
        <!-- 
1509
        <lst name="defaults">
1510
          <str name="hl.multiValuedSeparatorChar">/</str>
1511
        </lst>
1512
        -->
1513
      </fragmentsBuilder>
1514

    
1515
      <!-- multi-colored tag FragmentsBuilder -->
1516
      <fragmentsBuilder name="colored" 
1517
                        class="solr.highlight.ScoreOrderFragmentsBuilder">
1518
        <lst name="defaults">
1519
          <str name="hl.tag.pre"><![CDATA[
1520
               <b style="background:yellow">,<b style="background:lawgreen">,
1521
               <b style="background:aquamarine">,<b style="background:magenta">,
1522
               <b style="background:palegreen">,<b style="background:coral">,
1523
               <b style="background:wheat">,<b style="background:khaki">,
1524
               <b style="background:lime">,<b style="background:deepskyblue">]]></str>
1525
          <str name="hl.tag.post"><![CDATA[</b>]]></str>
1526
        </lst>
1527
      </fragmentsBuilder>
1528
      
1529
      <boundaryScanner name="default" 
1530
                       default="true"
1531
                       class="solr.highlight.SimpleBoundaryScanner">
1532
        <lst name="defaults">
1533
          <str name="hl.bs.maxScan">10</str>
1534
          <str name="hl.bs.chars">.,!? &#9;&#10;&#13;</str>
1535
        </lst>
1536
      </boundaryScanner>
1537
      
1538
      <boundaryScanner name="breakIterator" 
1539
                       class="solr.highlight.BreakIteratorBoundaryScanner">
1540
        <lst name="defaults">
1541
          <!-- type should be one of CHARACTER, WORD(default), LINE and SENTENCE -->
1542
          <str name="hl.bs.type">WORD</str>
1543
          <!-- language and country are used when constructing Locale object.  -->
1544
          <!-- And the Locale object will be used when getting instance of BreakIterator -->
1545
          <str name="hl.bs.language">en</str>
1546
          <str name="hl.bs.country">US</str>
1547
        </lst>
1548
      </boundaryScanner>
1549
    </highlighting>
1550
  </searchComponent>
1551

    
1552
  <!-- Update Processors
1553

1554
       Chains of Update Processor Factories for dealing with Update
1555
       Requests can be declared, and then used by name in Update
1556
       Request Processors
1557

1558
       http://wiki.apache.org/solr/UpdateRequestProcessor
1559

1560
    --> 
1561
  <!-- Deduplication
1562

1563
       An example dedup update processor that creates the "id" field
1564
       on the fly based on the hash code of some other fields.  This
1565
       example has overwriteDupes set to false since we are using the
1566
       id field as the signatureField and Solr will maintain
1567
       uniqueness based on that anyway.  
1568
       
1569
    -->
1570
  <!--
1571
     <updateRequestProcessorChain name="dedupe">
1572
       <processor class="solr.processor.SignatureUpdateProcessorFactory">
1573
         <bool name="enabled">true</bool>
1574
         <str name="signatureField">id</str>
1575
         <bool name="overwriteDupes">false</bool>
1576
         <str name="fields">name,features,cat</str>
1577
         <str name="signatureClass">solr.processor.Lookup3Signature</str>
1578
       </processor>
1579
       <processor class="solr.LogUpdateProcessorFactory" />
1580
       <processor class="solr.RunUpdateProcessorFactory" />
1581
     </updateRequestProcessorChain>
1582
    -->
1583
  
1584
  <!-- Language identification
1585

1586
       This example update chain identifies the language of the incoming
1587
       documents using the langid contrib. The detected language is
1588
       written to field language_s. No field name mapping is done.
1589
       The fields used for detection are text, title, subject and description,
1590
       making this example suitable for detecting languages form full-text
1591
       rich documents injected via ExtractingRequestHandler.
1592
       See more about langId at http://wiki.apache.org/solr/LanguageDetection
1593
    -->
1594
    <!--
1595
     <updateRequestProcessorChain name="langid">
1596
       <processor class="org.apache.solr.update.processor.TikaLanguageIdentifierUpdateProcessorFactory">
1597
         <str name="langid.fl">text,title,subject,description</str>
1598
         <str name="langid.langField">language_s</str>
1599
         <str name="langid.fallback">en</str>
1600
       </processor>
1601
       <processor class="solr.LogUpdateProcessorFactory" />
1602
       <processor class="solr.RunUpdateProcessorFactory" />
1603
     </updateRequestProcessorChain>
1604
    -->
1605

    
1606
  <!-- Script update processor
1607

1608
    This example hooks in an update processor implemented using JavaScript.
1609

1610
    See more about the script update processor at http://wiki.apache.org/solr/ScriptUpdateProcessor
1611
  -->
1612
  <!--
1613
    <updateRequestProcessorChain name="script">
1614
      <processor class="solr.StatelessScriptUpdateProcessorFactory">
1615
        <str name="script">update-script.js</str>
1616
        <lst name="params">
1617
          <str name="config_param">example config parameter</str>
1618
        </lst>
1619
      </processor>
1620
      <processor class="solr.RunUpdateProcessorFactory" />
1621
    </updateRequestProcessorChain>
1622
  -->
1623
 
1624
  <!-- Response Writers
1625

1626
       http://wiki.apache.org/solr/QueryResponseWriter
1627

1628
       Request responses will be written using the writer specified by
1629
       the 'wt' request parameter matching the name of a registered
1630
       writer.
1631

1632
       The "default" writer is the default and will be used if 'wt' is
1633
       not specified in the request.
1634
    -->
1635
  <!-- The following response writers are implicitly configured unless
1636
       overridden...
1637
    -->
1638
  <!--
1639
     <queryResponseWriter name="xml" 
1640
                          default="true"
1641
                          class="solr.XMLResponseWriter" />
1642
     <queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
1643
     <queryResponseWriter name="python" class="solr.PythonResponseWriter"/>
1644
     <queryResponseWriter name="ruby" class="solr.RubyResponseWriter"/>
1645
     <queryResponseWriter name="php" class="solr.PHPResponseWriter"/>
1646
     <queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/>
1647
     <queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
1648
     <queryResponseWriter name="schema.xml" class="solr.SchemaXmlResponseWriter"/>
1649
    -->
1650

    
1651
  <queryResponseWriter name="json" class="solr.JSONResponseWriter">
1652
     <!-- For the purposes of the tutorial, JSON responses are written as
1653
      plain text so that they are easy to read in *any* browser.
1654
      If you expect a MIME type of "application/json" just remove this override.
1655
     -->
1656
    <str name="content-type">text/plain; charset=UTF-8</str>
1657
  </queryResponseWriter>
1658
  
1659
  <!--
1660
     Custom response writers can be declared as needed...
1661
    -->
1662
    <queryResponseWriter name="velocity" class="solr.VelocityResponseWriter" startup="lazy"/>
1663
  
1664

    
1665
  <!-- XSLT response writer transforms the XML output by any xslt file found
1666
       in Solr's conf/xslt directory.  Changes to xslt files are checked for
1667
       every xsltCacheLifetimeSeconds.  
1668
    -->
1669
  <queryResponseWriter name="xslt" class="solr.XSLTResponseWriter">
1670
    <int name="xsltCacheLifetimeSeconds">5</int>
1671
  </queryResponseWriter>
1672

    
1673
  <!-- Query Parsers
1674

1675
       http://wiki.apache.org/solr/SolrQuerySyntax
1676

1677
       Multiple QParserPlugins can be registered by name, and then
1678
       used in either the "defType" param for the QueryComponent (used
1679
       by SearchHandler) or in LocalParams
1680
    -->
1681
  <!-- example of registering a query parser -->
1682
  <!--
1683
     <queryParser name="myparser" class="com.mycompany.MyQParserPlugin"/>
1684
    -->
1685

    
1686
  <!-- Function Parsers
1687

1688
       http://wiki.apache.org/solr/FunctionQuery
1689

1690
       Multiple ValueSourceParsers can be registered by name, and then
1691
       used as function names when using the "func" QParser.
1692
    -->
1693
  <!-- example of registering a custom function parser  -->
1694
  <!--
1695
     <valueSourceParser name="myfunc" 
1696
                        class="com.mycompany.MyValueSourceParser" />
1697
    -->
1698
    
1699
  
1700
  <!-- Document Transformers
1701
       http://wiki.apache.org/solr/DocTransformers
1702
    -->
1703
  <!--
1704
     Could be something like:
1705
     <transformer name="db" class="com.mycompany.LoadFromDatabaseTransformer" >
1706
       <int name="connection">jdbc://....</int>
1707
     </transformer>
1708
     
1709
     To add a constant value to all docs, use:
1710
     <transformer name="mytrans2" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
1711
       <int name="value">5</int>
1712
     </transformer>
1713
     
1714
     If you want the user to still be able to change it with _value:something_ use this:
1715
     <transformer name="mytrans3" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
1716
       <double name="defaultValue">5</double>
1717
     </transformer>
1718

1719
      If you are using the QueryElevationComponent, you may wish to mark documents that get boosted.  The
1720
      EditorialMarkerFactory will do exactly that:
1721
     <transformer name="qecBooster" class="org.apache.solr.response.transform.EditorialMarkerFactory" />
1722
    -->
1723
    
1724

    
1725
  <!-- Legacy config for the admin interface -->
1726
  <admin>
1727
    <defaultQuery>*:*</defaultQuery>
1728
  </admin>
1729

    
1730
</config>