1 <?xml version="1.0" encoding="UTF-8" ?>
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
10 http://www.apache.org/licenses/LICENSE-2.0
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.
20 This is the Solr schema file. This file should be named "schema.xml" and
21 should be in the conf directory under the solr home
22 (i.e. ./solr/conf/schema.xml by default)
23 or located where the classloader for the Solr webapp can find it.
25 This example schema is the recommended starting point for users.
26 It should be kept correct and concise, usable out-of-the-box.
28 For more information, on how to customize this file, please see
29 http://wiki.apache.org/solr/SchemaXml
31 PERFORMANCE NOTE: this schema includes many optional features and should not
32 be used for benchmarking. To improve performance one could
33 - set stored="false" for all fields possible (esp large fields) when you
34 only need to search on the field but don't need to return the original
36 - set indexed="false" if you don't need to search on the field, but only
37 return the field as a result of searching on other indexed fields.
38 - remove all unneeded copyField statements
39 - for best index size and searching performance, set "index" to false
40 for all general text fields, use copyField to copy them to the
41 catchall "text" field, and use that for searching.
42 - For maximum indexing performance, use the StreamingUpdateSolrServer
44 - Remember to run the JVM in server mode, and use a higher logging level
45 that avoids logging every request
48 <schema name="example-schemaless" version="1.5">
49 <!-- attribute "name" is the name of this schema and is only used for display purposes.
50 version="x.y" is Solr's version number for the schema syntax and
51 semantics. It should not normally be changed by applications.
53 1.0: multiValued attribute did not exist, all fields are multiValued
55 1.1: multiValued attribute introduced, false by default
56 1.2: omitTermFreqAndPositions attribute introduced, true by default
57 except for text fields.
58 1.3: removed optional field compress feature
59 1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser
60 behavior when a single string produces multiple tokens. Defaults
61 to off for version >= 1.4
62 1.5: omitNorms defaults to true for primitive field types
63 (int, float, boolean, string...)
67 <!-- Valid attributes for fields:
68 name: mandatory - the name for the field
69 type: mandatory - the name of a field type from the
70 <types> fieldType section
71 indexed: true if this field should be indexed (searchable or sortable)
72 stored: true if this field should be retrievable
73 docValues: true if this field should have doc values. Doc values are
74 useful for faceting, grouping, sorting and function queries. Although not
75 required, doc values will make the index faster to load, more
76 NRT-friendly and more memory-efficient. They however come with some
77 limitations: they are currently only supported by StrField, UUIDField
78 and all Trie*Fields, and depending on the field type, they might
79 require the field to be single-valued, be required or have a default
80 value (check the documentation of the field type you're interested in
82 multiValued: true if this field may contain multiple values per document
83 omitNorms: (expert) set to true to omit the norms associated with
84 this field (this disables length normalization and index-time
85 boosting for the field, and saves some memory). Only full-text
86 fields or fields that need an index-time boost need norms.
87 Norms are omitted for primitive (non-analyzed) types by default.
88 termVectors: [false] set to true to store the term vector for a
90 When using MoreLikeThis, fields used for similarity should be
91 stored for best performance.
92 termPositions: Store position information with the term vector.
93 This will increase storage costs.
94 termOffsets: Store offset information with the term vector. This
95 will increase storage costs.
96 required: The field is required. It will throw an error if the
98 default: a value that should be used if no value is specified
99 when adding a document.
102 <!-- field names should consist of alphanumeric or underscore characters only and
103 not start with a digit. This is not currently strictly enforced,
104 but other field names will not have first class support from all components
105 and back compatibility is not guaranteed. Names with both leading and
106 trailing underscores (e.g. _version_) are reserved.
109 <!-- In this "schemaless" example, only two fields are pre-declared: id and _version_.
110 All other fields will be type guessed and added via the
111 "add-unknown-fields-to-the-schema" update request processor chain declared
114 <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
115 <field name="_version_" type="long" indexed="true" stored="true"/>
118 <!-- Dynamic field definitions allow using convention over configuration
119 for fields via the specification of patterns to match field names.
120 EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
121 RESTRICTION: the glob-like pattern in the name attribute must have
122 a "*" only at the start or the end. -->
124 <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
125 <dynamicField name="*_is" type="int" indexed="true" stored="true" multiValued="true"/>
126 <dynamicField name="*_s" type="string" indexed="true" stored="true" />
127 <dynamicField name="*_ss" type="string" indexed="true" stored="true" multiValued="true"/>
128 <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
129 <dynamicField name="*_ls" type="long" indexed="true" stored="true" multiValued="true"/>
130 <dynamicField name="*_t" type="text_general" indexed="true" stored="true"/>
131 <dynamicField name="*_txt" type="text_general" indexed="true" stored="true" multiValued="true"/>
132 <dynamicField name="*_en" type="text_en" indexed="true" stored="true" multiValued="true"/>
133 <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
134 <dynamicField name="*_bs" type="boolean" indexed="true" stored="true" multiValued="true"/>
135 <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
136 <dynamicField name="*_fs" type="float" indexed="true" stored="true" multiValued="true"/>
137 <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
138 <dynamicField name="*_ds" type="double" indexed="true" stored="true" multiValued="true"/>
140 <!-- Type used to index the lat and lon components for the "location" FieldType -->
141 <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false" />
143 <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
144 <dynamicField name="*_dts" type="date" indexed="true" stored="true" multiValued="true"/>
145 <dynamicField name="*_p" type="location" indexed="true" stored="true"/>
147 <!-- some trie-coded dynamic fields for faster range queries -->
148 <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
149 <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
150 <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
151 <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
152 <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
154 <dynamicField name="*_pi" type="pint" indexed="true" stored="true"/>
155 <dynamicField name="*_c" type="currency" indexed="true" stored="true"/>
157 <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
158 <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
160 <dynamicField name="random_*" type="random" />
162 <!-- uncomment the following to ignore any fields that don't already match an existing
163 field name or dynamic field, rather than reporting them as an error.
164 alternately, change the type="ignored" to some other type e.g. "text" if you want
165 unknown fields indexed and/or stored by default
167 NB: use of "*" dynamic fields will disable field type guessing and adding
168 unknown fields to the schema. -->
169 <!--dynamicField name="*" type="ignored" multiValued="true" /-->
174 <!-- Field to use to determine and enforce document uniqueness.
175 Unless this field is marked with required="false", it will be a required field
177 <uniqueKey>id</uniqueKey>
179 <!-- DEPRECATED: The defaultSearchField is consulted by various query parsers when
180 parsing a query string that isn't explicit about the field. Machine (non-user)
181 generated queries are best made explicit, or they can use the "df" request parameter
182 which takes precedence over this.
183 Note: Un-commenting defaultSearchField will be insufficient if your request handler
184 in solrconfig.xml defines "df", which takes precedence. That would need to be removed.
185 <defaultSearchField>text</defaultSearchField> -->
187 <!-- DEPRECATED: The defaultOperator (AND|OR) is consulted by various query parsers
188 when parsing a query string to determine if a clause of the query should be marked as
189 required or optional, assuming the clause isn't already marked by some operator.
190 The default is OR, which is generally assumed so it is not a good idea to change it
191 globally here. The "q.op" request parameter takes precedence over this.
192 <solrQueryParser defaultOperator="OR"/> -->
194 <!-- copyField commands copy one field to another at the time a document
195 is added to the index. It's used either to index the same field differently,
196 or to add multiple fields to the same field for easier/faster searching.
198 <copyField source="cat" dest="text"/>
199 <copyField source="name" dest="text"/>
200 <copyField source="manu" dest="text"/>
201 <copyField source="features" dest="text"/>
202 <copyField source="includes" dest="text"/>
203 <copyField source="manu" dest="manu_exact"/>
206 <!-- Copy the price into a currency enabled field (default USD)
207 <copyField source="price" dest="price_c"/>
210 <!-- Text fields from SolrCell to search by default in our catch-all field
211 <copyField source="title" dest="text"/>
212 <copyField source="author" dest="text"/>
213 <copyField source="description" dest="text"/>
214 <copyField source="keywords" dest="text"/>
215 <copyField source="content" dest="text"/>
216 <copyField source="content_type" dest="text"/>
217 <copyField source="resourcename" dest="text"/>
218 <copyField source="url" dest="text"/>
221 <!-- Create a string version of author for faceting
222 <copyField source="author" dest="author_s"/>
225 <!-- Above, multiple source fields are copied to the [text] field.
226 Another way to map multiple source fields to the same
227 destination field is to use the dynamic field syntax.
228 copyField also supports a maxChars to copy setting. -->
230 <!-- <copyField source="*_t" dest="text" maxChars="3000"/> -->
232 <!-- copy name to alphaNameSort, a field designed for sorting by name -->
233 <!-- <copyField source="name" dest="alphaNameSort"/> -->
236 <!-- field type definitions. The "name" attribute is
237 just a label to be used by field definitions. The "class"
238 attribute and any other attributes determine the real
239 behavior of the fieldType.
240 Class names starting with "solr" refer to java classes in a
241 standard package such as org.apache.solr.analysis
244 <!-- The StrField type is not analyzed, but indexed/stored verbatim.
245 It supports doc values but in that case the field needs to be
246 single-valued and either required or have a default value.
248 <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
250 <!-- boolean type: "true" or "false" -->
251 <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
253 <fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
255 <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
256 currently supported on types that are sorted internally as strings
257 and on numeric types.
258 This includes "string","boolean", and, as of 3.5 (and 4.x),
259 int, float, long, date, double, including the "Trie" variants.
260 - If sortMissingLast="true", then a sort on this field will cause documents
261 without the field to come after documents with the field,
262 regardless of the requested sort order (asc or desc).
263 - If sortMissingFirst="true", then a sort on this field will cause documents
264 without the field to come before documents with the field,
265 regardless of the requested sort order.
266 - If sortMissingLast="false" and sortMissingFirst="false" (the default),
267 then default lucene sorting will be used which places docs without the
268 field first in an ascending sort and last in a descending sort.
272 Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
274 These fields support doc values, but they require the field to be
275 single-valued and either be required or have a default value.
277 <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
278 <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
279 <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
280 <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
283 Numeric field types that index each value at various levels of precision
284 to accelerate range queries when the number of values between the range
285 endpoints is large. See the javadoc for NumericRangeQuery for internal
286 implementation details.
288 Smaller precisionStep values (specified in bits) will lead to more tokens
289 indexed per value, slightly larger index size, and faster range queries.
290 A precisionStep of 0 disables indexing at different precision levels.
292 <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
293 <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
294 <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
295 <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
297 <fieldType name="tints" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
298 <fieldType name="tfloats" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
299 <fieldType name="tlongs" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
300 <fieldType name="tdoubles" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
302 <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
303 is a more restricted form of the canonical representation of dateTime
304 http://www.w3.org/TR/xmlschema-2/#dateTime
305 The trailing "Z" designates UTC time and is mandatory.
306 Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
307 All other components are mandatory.
309 Expressions can also be used to denote calculations that should be
310 performed relative to "NOW" to determine the value, ie...
313 ... Round to the start of the current hour
315 ... Exactly 1 day prior to now
316 NOW/DAY+6MONTHS+3DAYS
317 ... 6 months and 3 days in the future from the start of
320 Consult the DateField javadocs for more information.
322 Note: For faster range queries, consider the tdate type
324 <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
326 <!-- A Trie based date field for faster date range queries and date faceting. -->
327 <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
329 <fieldType name="tdates" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0" multiValued="true"/>
332 <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
333 <fieldtype name="binary" class="solr.BinaryField"/>
337 These should only be used for compatibility with existing indexes (created with lucene or older Solr versions).
338 Use Trie based fields instead. As of Solr 3.5 and 4.x, Trie based fields support sortMissingFirst/Last
340 Plain numeric field types that store and index the text
341 value verbatim (and hence don't correctly support range queries, since the
342 lexicographic ordering isn't equal to the numeric ordering)
344 <fieldType name="pint" class="solr.IntField"/>
345 <fieldType name="plong" class="solr.LongField"/>
346 <fieldType name="pfloat" class="solr.FloatField"/>
347 <fieldType name="pdouble" class="solr.DoubleField"/>
348 <fieldType name="pdate" class="solr.DateField" sortMissingLast="true"/>
350 <!-- The "RandomSortField" is not used to store or search any
351 data. You can declare fields of this type it in your schema
352 to generate pseudo-random orderings of your docs for sorting
353 or function purposes. The ordering is generated based on the field
354 name and the version of the index. As long as the index version
355 remains unchanged, and the same field name is reused,
356 the ordering of the docs will be consistent.
357 If you want different psuedo-random orderings of documents,
358 for the same version of the index, use a dynamicField and
359 change the field name in the request.
361 <fieldType name="random" class="solr.RandomSortField" indexed="true" />
363 <!-- solr.TextField allows the specification of custom text analyzers
364 specified as a tokenizer and a list of token filters. Different
365 analyzers may be specified for indexing and querying.
367 The optional positionIncrementGap puts space between multiple fields of
368 this type on the same document, with the purpose of preventing false phrase
369 matching across fields.
371 For more info on customizing your analyzer chain, please see
372 http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
375 <!-- One can also specify an existing Analyzer class that has a
376 default constructor via the class attribute on the analyzer element.
378 <fieldType name="text_greek" class="solr.TextField">
379 <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
383 <!-- A text field that only splits on whitespace for exact matching of words -->
384 <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
386 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
390 <!-- A general text field that has reasonable, generic
391 cross-language defaults: it tokenizes with StandardTokenizer,
392 removes stop words from case-insensitive "stopwords.txt"
393 (empty by default), and down cases. At query time only, it
394 also applies synonyms. -->
395 <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100" multiValued="true">
396 <analyzer type="index">
397 <tokenizer class="solr.StandardTokenizerFactory"/>
398 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
399 <!-- in this example, we will only use synonyms at query time
400 <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
402 <filter class="solr.LowerCaseFilterFactory"/>
404 <analyzer type="query">
405 <tokenizer class="solr.StandardTokenizerFactory"/>
406 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
407 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
408 <filter class="solr.LowerCaseFilterFactory"/>
412 <!-- A text field with defaults appropriate for English: it
413 tokenizes with StandardTokenizer, removes English stop words
414 (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
415 finally applies Porter's stemming. The query time analyzer
416 also applies synonyms from synonyms.txt. -->
417 <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
418 <analyzer type="index">
419 <tokenizer class="solr.StandardTokenizerFactory"/>
420 <!-- in this example, we will only use synonyms at query time
421 <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
423 <!-- Case insensitive stop word removal.
425 <filter class="solr.StopFilterFactory"
427 words="lang/stopwords_en.txt"
429 <filter class="solr.LowerCaseFilterFactory"/>
430 <filter class="solr.EnglishPossessiveFilterFactory"/>
431 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
432 <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
433 <filter class="solr.EnglishMinimalStemFilterFactory"/>
435 <filter class="solr.PorterStemFilterFactory"/>
437 <analyzer type="query">
438 <tokenizer class="solr.StandardTokenizerFactory"/>
439 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
440 <filter class="solr.StopFilterFactory"
442 words="lang/stopwords_en.txt"
444 <filter class="solr.LowerCaseFilterFactory"/>
445 <filter class="solr.EnglishPossessiveFilterFactory"/>
446 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
447 <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
448 <filter class="solr.EnglishMinimalStemFilterFactory"/>
450 <filter class="solr.PorterStemFilterFactory"/>
454 <!-- A text field with defaults appropriate for English, plus
455 aggressive word-splitting and autophrase features enabled.
456 This field is just like text_en, except it adds
457 WordDelimiterFilter to enable splitting and matching of
458 words on case-change, alpha numeric boundaries, and
459 non-alphanumeric chars. This means certain compound word
460 cases will work, for example query "wi fi" will match
461 document "WiFi" or "wi-fi".
463 <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
464 <analyzer type="index">
465 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
466 <!-- in this example, we will only use synonyms at query time
467 <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
469 <!-- Case insensitive stop word removal.
471 <filter class="solr.StopFilterFactory"
473 words="lang/stopwords_en.txt"
475 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
476 <filter class="solr.LowerCaseFilterFactory"/>
477 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
478 <filter class="solr.PorterStemFilterFactory"/>
480 <analyzer type="query">
481 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
482 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
483 <filter class="solr.StopFilterFactory"
485 words="lang/stopwords_en.txt"
487 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
488 <filter class="solr.LowerCaseFilterFactory"/>
489 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
490 <filter class="solr.PorterStemFilterFactory"/>
494 <!-- Less flexible matching, but less false matches. Probably not ideal for product names,
495 but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
496 <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
498 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
499 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
500 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
501 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
502 <filter class="solr.LowerCaseFilterFactory"/>
503 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
504 <filter class="solr.EnglishMinimalStemFilterFactory"/>
505 <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
506 possible with WordDelimiterFilter in conjuncton with stemming. -->
507 <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
511 <!-- Just like text_general except it reverses the characters of
512 each token, to enable more efficient leading wildcard queries. -->
513 <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
514 <analyzer type="index">
515 <tokenizer class="solr.StandardTokenizerFactory"/>
516 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
517 <filter class="solr.LowerCaseFilterFactory"/>
518 <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
519 maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
521 <analyzer type="query">
522 <tokenizer class="solr.StandardTokenizerFactory"/>
523 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
524 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
525 <filter class="solr.LowerCaseFilterFactory"/>
529 <!-- charFilter + WhitespaceTokenizer -->
531 <fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
533 <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
534 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
539 <!-- This is an example of using the KeywordTokenizer along
540 With various TokenFilterFactories to produce a sortable field
541 that does not include some properties of the source text
543 <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
545 <!-- KeywordTokenizer does no actual tokenizing, so the entire
546 input string is preserved as a single token
548 <tokenizer class="solr.KeywordTokenizerFactory"/>
549 <!-- The LowerCase TokenFilter does what you expect, which can be
550 when you want your sorting to be case insensitive
552 <filter class="solr.LowerCaseFilterFactory" />
553 <!-- The TrimFilter removes any leading or trailing whitespace -->
554 <filter class="solr.TrimFilterFactory" />
555 <!-- The PatternReplaceFilter gives you the flexibility to use
556 Java Regular expression to replace any sequence of characters
557 matching a pattern with an arbitrary replacement string,
558 which may include back references to portions of the original
559 string matched by the pattern.
561 See the Java Regular Expression documentation for more
562 information on pattern and replacement string syntax.
564 http://docs.oracle.com/javase/7/docs/api/java/util/regex/package-summary.html
566 <filter class="solr.PatternReplaceFilterFactory"
567 pattern="([^a-z])" replacement="" replace="all"
572 <fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
574 <tokenizer class="solr.StandardTokenizerFactory"/>
575 <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
579 <fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
581 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
583 The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
584 a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
585 Attributes of the DelimitedPayloadTokenFilterFactory :
586 "delimiter" - a one character delimiter. Default is | (pipe)
587 "encoder" - how to encode the following value into a playload
588 float -> org.apache.lucene.analysis.payloads.FloatEncoder,
589 integer -> o.a.l.a.p.IntegerEncoder
590 identity -> o.a.l.a.p.IdentityEncoder
591 Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
593 <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
597 <!-- lowercases the entire field value, keeping it as a single token. -->
598 <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
600 <tokenizer class="solr.KeywordTokenizerFactory"/>
601 <filter class="solr.LowerCaseFilterFactory" />
606 Example of using PathHierarchyTokenizerFactory at index time, so
607 queries for paths match documents at that path, or in descendent paths
609 <fieldType name="descendent_path" class="solr.TextField">
610 <analyzer type="index">
611 <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
613 <analyzer type="query">
614 <tokenizer class="solr.KeywordTokenizerFactory" />
618 Example of using PathHierarchyTokenizerFactory at query time, so
619 queries for paths match documents at that path, or in ancestor paths
621 <fieldType name="ancestor_path" class="solr.TextField">
622 <analyzer type="index">
623 <tokenizer class="solr.KeywordTokenizerFactory" />
625 <analyzer type="query">
626 <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
630 <!-- since fields of this type are by default not stored or indexed,
631 any data added to them will be ignored outright. -->
632 <fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
634 <!-- This point type indexes the coordinates as separate fields (subFields)
635 If subFieldType is defined, it references a type, and a dynamic field
636 definition is created matching *___<typename>. Alternately, if
637 subFieldSuffix is defined, that is used to create the subFields.
638 Example: if subFieldType="double", then the coordinates would be
639 indexed in fields myloc_0___double,myloc_1___double.
640 Example: if subFieldSuffix="_d" then the coordinates would be indexed
641 in fields myloc_0_d,myloc_1_d
642 The subFields are an implementation detail of the fieldType, and end
643 users normally should not need to know about them.
645 <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
647 <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
648 <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
650 <!-- An alternative geospatial field type new to Solr 4. It supports multiValued and polygon shapes.
651 For more information about this and other Spatial fields new to Solr 4, see:
652 http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
654 <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
655 geo="true" distErrPct="0.025" maxDistErr="0.000009" units="degrees" />
657 <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
659 defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
660 precisionStep: Specifies the precisionStep for the TrieLong field used for the amount
661 providerClass: Lets you plug in other exchange provider backend:
662 solr.FileExchangeRateProvider is the default and takes one parameter:
663 currencyConfig: name of an xml file holding exchange rates
664 solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
665 ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
666 refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
668 <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
672 <!-- some examples for different languages (generally ordered by ISO code) -->
675 <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
677 <tokenizer class="solr.StandardTokenizerFactory"/>
678 <!-- for any non-arabic -->
679 <filter class="solr.LowerCaseFilterFactory"/>
680 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
681 <!-- normalizes ﻯ to ﻱ, etc -->
682 <filter class="solr.ArabicNormalizationFilterFactory"/>
683 <filter class="solr.ArabicStemFilterFactory"/>
688 <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
690 <tokenizer class="solr.StandardTokenizerFactory"/>
691 <filter class="solr.LowerCaseFilterFactory"/>
692 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" />
693 <filter class="solr.BulgarianStemFilterFactory"/>
698 <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
700 <tokenizer class="solr.StandardTokenizerFactory"/>
701 <!-- removes l', etc -->
702 <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
703 <filter class="solr.LowerCaseFilterFactory"/>
704 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" />
705 <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
709 <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
710 <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
712 <tokenizer class="solr.StandardTokenizerFactory"/>
713 <!-- normalize width before bigram, as e.g. half-width dakuten combine -->
714 <filter class="solr.CJKWidthFilterFactory"/>
715 <!-- for any non-CJK -->
716 <filter class="solr.LowerCaseFilterFactory"/>
717 <filter class="solr.CJKBigramFilterFactory"/>
722 <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
724 <tokenizer class="solr.StandardTokenizerFactory"/>
725 <filter class="solr.LowerCaseFilterFactory"/>
726 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" />
727 <filter class="solr.CzechStemFilterFactory"/>
732 <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
734 <tokenizer class="solr.StandardTokenizerFactory"/>
735 <filter class="solr.LowerCaseFilterFactory"/>
736 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
737 <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
742 <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
744 <tokenizer class="solr.StandardTokenizerFactory"/>
745 <filter class="solr.LowerCaseFilterFactory"/>
746 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" />
747 <filter class="solr.GermanNormalizationFilterFactory"/>
748 <filter class="solr.GermanLightStemFilterFactory"/>
749 <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
750 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
755 <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
757 <tokenizer class="solr.StandardTokenizerFactory"/>
758 <!-- greek specific lowercase for sigma -->
759 <filter class="solr.GreekLowerCaseFilterFactory"/>
760 <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
761 <filter class="solr.GreekStemFilterFactory"/>
766 <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
768 <tokenizer class="solr.StandardTokenizerFactory"/>
769 <filter class="solr.LowerCaseFilterFactory"/>
770 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
771 <filter class="solr.SpanishLightStemFilterFactory"/>
772 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
777 <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
779 <tokenizer class="solr.StandardTokenizerFactory"/>
780 <filter class="solr.LowerCaseFilterFactory"/>
781 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" />
782 <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
787 <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
790 <charFilter class="solr.PersianCharFilterFactory"/>
791 <tokenizer class="solr.StandardTokenizerFactory"/>
792 <filter class="solr.LowerCaseFilterFactory"/>
793 <filter class="solr.ArabicNormalizationFilterFactory"/>
794 <filter class="solr.PersianNormalizationFilterFactory"/>
795 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" />
800 <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
802 <tokenizer class="solr.StandardTokenizerFactory"/>
803 <filter class="solr.LowerCaseFilterFactory"/>
804 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
805 <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
806 <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
811 <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
813 <tokenizer class="solr.StandardTokenizerFactory"/>
814 <!-- removes l', etc -->
815 <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
816 <filter class="solr.LowerCaseFilterFactory"/>
817 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
818 <filter class="solr.FrenchLightStemFilterFactory"/>
819 <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
820 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
825 <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
827 <tokenizer class="solr.StandardTokenizerFactory"/>
828 <!-- removes d', etc -->
829 <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
830 <!-- removes n-, etc. position increments is intentionally false! -->
831 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
832 <filter class="solr.IrishLowerCaseFilterFactory"/>
833 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/>
834 <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
839 <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
841 <tokenizer class="solr.StandardTokenizerFactory"/>
842 <filter class="solr.LowerCaseFilterFactory"/>
843 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" />
844 <filter class="solr.GalicianStemFilterFactory"/>
845 <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
850 <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
852 <tokenizer class="solr.StandardTokenizerFactory"/>
853 <filter class="solr.LowerCaseFilterFactory"/>
854 <!-- normalizes unicode representation -->
855 <filter class="solr.IndicNormalizationFilterFactory"/>
856 <!-- normalizes variation in spelling -->
857 <filter class="solr.HindiNormalizationFilterFactory"/>
858 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
859 <filter class="solr.HindiStemFilterFactory"/>
864 <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
866 <tokenizer class="solr.StandardTokenizerFactory"/>
867 <filter class="solr.LowerCaseFilterFactory"/>
868 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
869 <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
870 <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
875 <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
877 <tokenizer class="solr.StandardTokenizerFactory"/>
878 <filter class="solr.LowerCaseFilterFactory"/>
879 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" />
880 <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
885 <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
887 <tokenizer class="solr.StandardTokenizerFactory"/>
888 <filter class="solr.LowerCaseFilterFactory"/>
889 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" />
890 <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
891 <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
896 <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
898 <tokenizer class="solr.StandardTokenizerFactory"/>
899 <!-- removes l', etc -->
900 <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
901 <filter class="solr.LowerCaseFilterFactory"/>
902 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
903 <filter class="solr.ItalianLightStemFilterFactory"/>
904 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
908 <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
910 NOTE: If you want to optimize search for precision, use default operator AND in your query
911 parser config with <solrQueryParser defaultOperator="AND"/> further down in this file. Use
912 OR if you would like to optimize for recall (default).
914 <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
916 <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
918 Kuromoji has a search mode (default) that does segmentation useful for search. A heuristic
919 is used to segment compounds into its parts and the compound itself is kept as synonym.
921 Valid values for attribute mode are:
922 normal: regular segmentation
923 search: segmentation useful for search with synonyms compounds (default)
924 extended: same as search mode, but unigrams unknown words (experimental)
926 For some applications it might be good to use search mode for indexing and normal mode for
927 queries to reduce recall and prevent parts of compounds from being matched and highlighted.
928 Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
930 Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
931 model with your own entries for segmentation, part-of-speech tags and readings without a need
932 to specify weights. Notice that user dictionaries have not been subject to extensive testing.
934 User dictionary attributes are:
935 userDictionary: user dictionary filename
936 userDictionaryEncoding: user dictionary encoding (default is UTF-8)
938 See lang/userdict_ja.txt for a sample user dictionary file.
940 Punctuation characters are discarded by default. Use discardPunctuation="false" to keep them.
942 See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
944 <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
945 <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
946 <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
947 <filter class="solr.JapaneseBaseFormFilterFactory"/>
948 <!-- Removes tokens with certain part-of-speech tags -->
949 <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
950 <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
951 <filter class="solr.CJKWidthFilterFactory"/>
952 <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
953 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" />
954 <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
955 <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
956 <!-- Lower-cases romaji characters -->
957 <filter class="solr.LowerCaseFilterFactory"/>
962 <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
964 <tokenizer class="solr.StandardTokenizerFactory"/>
965 <filter class="solr.LowerCaseFilterFactory"/>
966 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" />
967 <filter class="solr.LatvianStemFilterFactory"/>
972 <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
974 <tokenizer class="solr.StandardTokenizerFactory"/>
975 <filter class="solr.LowerCaseFilterFactory"/>
976 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
977 <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
978 <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
983 <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
985 <tokenizer class="solr.StandardTokenizerFactory"/>
986 <filter class="solr.LowerCaseFilterFactory"/>
987 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
988 <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
989 <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> -->
990 <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
995 <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
997 <tokenizer class="solr.StandardTokenizerFactory"/>
998 <filter class="solr.LowerCaseFilterFactory"/>
999 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
1000 <filter class="solr.PortugueseLightStemFilterFactory"/>
1001 <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
1002 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
1003 <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
1008 <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
1010 <tokenizer class="solr.StandardTokenizerFactory"/>
1011 <filter class="solr.LowerCaseFilterFactory"/>
1012 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" />
1013 <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
1018 <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
1020 <tokenizer class="solr.StandardTokenizerFactory"/>
1021 <filter class="solr.LowerCaseFilterFactory"/>
1022 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
1023 <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
1024 <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
1029 <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
1031 <tokenizer class="solr.StandardTokenizerFactory"/>
1032 <filter class="solr.LowerCaseFilterFactory"/>
1033 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
1034 <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
1035 <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
1040 <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
1042 <tokenizer class="solr.StandardTokenizerFactory"/>
1043 <filter class="solr.LowerCaseFilterFactory"/>
1044 <filter class="solr.ThaiWordFilterFactory"/>
1045 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" />
1050 <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
1052 <tokenizer class="solr.StandardTokenizerFactory"/>
1053 <filter class="solr.TurkishLowerCaseFilterFactory"/>
1054 <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
1055 <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
1061 <!-- Similarity is the scoring routine for each document vs. a query.
1062 A custom Similarity or SimilarityFactory may be specified here, but
1063 the default is fine for most applications.
1064 For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
1067 <similarity class="com.example.solr.CustomSimilarityFactory">
1068 <str name="paramkey">param value</str>