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" 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 semantics. It should
51 not normally be changed by applications.
52 1.0: multiValued attribute did not exist, all fields are multiValued by nature
53 1.1: multiValued attribute introduced, false by default
54 1.2: omitTermFreqAndPositions attribute introduced, true by default except for text fields.
55 1.3: removed optional field compress feature
56 1.4: default auto-phrase (QueryParser feature) to off
57 1.5: omitNorms defaults to true for primitive field types (int, float, boolean, string...)
61 <!-- Valid attributes for fields:
62 name: mandatory - the name for the field
63 type: mandatory - the name of a field type from the
64 <types> fieldType section
65 indexed: true if this field should be indexed (searchable or sortable)
66 stored: true if this field should be retrievable
67 multiValued: true if this field may contain multiple values per document
68 omitNorms: (expert) set to true to omit the norms associated with
69 this field (this disables length normalization and index-time
70 boosting for the field, and saves some memory). Only full-text
71 fields or fields that need an index-time boost need norms.
72 Norms are omitted for primitive (non-analyzed) types by default.
73 termVectors: [false] set to true to store the term vector for a
75 When using MoreLikeThis, fields used for similarity should be
76 stored for best performance.
77 termPositions: Store position information with the term vector.
78 This will increase storage costs.
79 termOffsets: Store offset information with the term vector. This
80 will increase storage costs.
81 required: The field is required. It will throw an error if the
83 default: a value that should be used if no value is specified
84 when adding a document.
87 <!-- field names should consist of alphanumeric or underscore characters only and
88 not start with a digit. This is not currently strictly enforced,
89 but other field names will not have first class support from all components
90 and back compatibility is not guaranteed. Names with both leading and
91 trailing underscores (e.g. _version_) are reserved.
94 <!-- <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" /> -->
95 <!-- <field name="sku" type="text_en_splitting_tight" indexed="true" stored="true" omitNorms="true"/> -->
96 <!-- <field name="name" type="text_general" indexed="true" stored="true"/> -->
97 <!-- <field name="manu" type="text_general" indexed="true" stored="true" omitNorms="true"/> -->
98 <!-- <field name="cat" type="string" indexed="true" stored="true" multiValued="true"/> -->
99 <!-- <field name="features" type="text_general" indexed="true" stored="true" multiValued="true"/> -->
100 <!-- <field name="includes" type="text_general" indexed="true" stored="true" termVectors="true" termPositions="true" termOffsets="true" /> -->
102 <!-- <field name="weight" type="float" indexed="true" stored="true"/> -->
103 <!-- <field name="price" type="float" indexed="true" stored="true"/> -->
104 <!-- <field name="popularity" type="int" indexed="true" stored="true" /> -->
105 <!-- <field name="inStock" type="boolean" indexed="true" stored="true" /> -->
107 <!-- <field name="store" type="location" indexed="true" stored="true"/> -->
109 <!-- Common metadata fields, named specifically to match up with
110 SolrCell metadata when parsing rich documents such as Word, PDF.
111 Some fields are multiValued only because Tika currently may return
112 multiple values for them. Some metadata is parsed from the documents,
113 but there are some which come from the client context:
114 "content_type": From the HTTP headers of incoming stream
115 "resourcename": From SolrCell request param resource.name
117 <!-- <field name="title" type="text_general" indexed="true" stored="true" multiValued="true"/> -->
118 <!-- <field name="subject" type="text_general" indexed="true" stored="true"/> -->
119 <!-- <field name="description" type="text_general" indexed="true" stored="true"/> -->
120 <!-- <field name="comments" type="text_general" indexed="true" stored="true"/> -->
121 <!-- <field name="author" type="text_general" indexed="true" stored="true"/> -->
122 <!-- <field name="keywords" type="text_general" indexed="true" stored="true"/> -->
123 <!-- <field name="category" type="text_general" indexed="true" stored="true"/> -->
124 <!-- <field name="resourcename" type="text_general" indexed="true" stored="true"/> -->
125 <!-- <field name="url" type="text_general" indexed="true" stored="true"/> -->
126 <!-- <field name="content_type" type="string" indexed="true" stored="true" multiValued="true"/> -->
127 <!-- <field name="last_modified" type="date" indexed="true" stored="true"/> -->
128 <!-- <field name="links" type="string" indexed="true" stored="true" multiValued="true"/> -->
130 <field name="book_id" type="int" indexed="true" stored="true" />
131 <field name="parent_id" type="int" indexed="false" stored="true" />
132 <field name="slug" type="text_general" stored="false" indexed="true" omitNorms="true"/> <!-- no norms -->
133 <field name="tags" type="lowercase" stored="false" indexed="true" multiValued="true"/>
134 <field name="is_book" type="boolean" stored="false" indexed="true"/>
135 <field name="authors" type="text_general" stored="false" indexed="true" multiValued="true" termPositions="true" termVectors="true"/>
136 <field name="translators" type="text_general" stored="false" indexed="true" multiValued="true" termPositions="true" termVectors="true" />
137 <field name="title" type="text_pl" stored="false" indexed="true"/>
138 <field name="title_orig" type="text_general" stored="false" indexed="true"/>
139 <!-- <field name="published_date" type="tdate" stored="false" indexed="true"/>-->
140 <field name="published_date" type="string" stored="true" indexed="true"/>
142 <field name="themes" type="lowercase" stored="true" intexed="true" termVectors="true" termPositions="true" multiValued="true" />
143 <field name="themes_pl" type="text_pl" stored="true" indexed="true" termVectors="true" termPositions="true" multiValued="true" />
144 <field name="header_index" type="int" stored="true" indexed="true"/>
145 <field name="header_span" type="int" stored="true" indexed="true"/>
146 <field name="header_type" type="lowercase" stored="true" indexed="false"/>
147 <field name="text" type="text_pl" stored="false" indexed="true" termPositions="true" />
149 <field name="snippets_position" type="int" stored="true" indexed="false"/>
150 <field name="snippets_length" type="int" stored="true" indexed="false"/>
151 <field name="snippets_revision" type="int" stored="true" indexed="false"/>
152 <field name="fragment_anchor" type="string" stored="true" indexed="false"/>
154 <field name="tag_id" type="int" stored="true" indexed="true"/>
155 <field name="tag_name" type="lowercase" stored="true" intexed="true" />
156 <field name="tag_name_pl" type="text_pl" stored="false" indexed="true" multiValued="true"/>
157 <field name="tag_category" type="string" stored="true" indexed="true" />
158 <field name="is_pdcounter" type="boolean" stored="true" indexed="true" />
160 <!-- Main body of document extracted by SolrCell.
161 NOTE: This field is not indexed by default, since it is also copied to "text"
162 using copyField below. This is to save space. Use this field for returning and
163 highlighting document content. Use the "text" field to search the content. -->
164 <!-- <field name="content" type="text_general" indexed="false" stored="true" multiValued="true"/> -->
167 <!-- catchall field, containing all other searchable text fields (implemented
168 via copyField further on in this schema -->
169 <!-- <field name="text" type="text_general" indexed="true" stored="false" multiValued="true"/> -->
171 <!-- catchall text field that indexes tokens both normally and in reverse for efficient
172 leading wildcard queries. -->
173 <!-- <field name="text_rev" type="text_general_rev" indexed="true" stored="false" multiValued="true"/> -->
175 <!-- non-tokenized version of manufacturer to make it easier to sort or group
176 results by manufacturer. copied from "manu" via copyField -->
177 <!-- <field name="manu_exact" type="string" indexed="true" stored="false"/> -->
179 <!-- <field name="payloads" type="payloads" indexed="true" stored="true"/> -->
181 <!-- <field name="_version_" type="long" indexed="true" stored="true"/> -->
183 <!-- Uncommenting the following will create a "timestamp" field using
184 a default value of "NOW" to indicate when each document was indexed.
187 <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
190 <!-- Dynamic field definitions allow using convention over configuration
191 for fields via the specification of patterns to match field names.
192 EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
193 RESTRICTION: the glob-like pattern in the name attribute must have
194 a "*" only at the start or the end. -->
196 <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
197 <dynamicField name="*_is" type="int" indexed="true" stored="true" multiValued="true"/>
198 <dynamicField name="*_s" type="string" indexed="true" stored="true" />
199 <dynamicField name="*_ss" type="string" indexed="true" stored="true" multiValued="true"/>
200 <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
201 <dynamicField name="*_ls" type="long" indexed="true" stored="true" multiValued="true"/>
202 <dynamicField name="*_t" type="text_general" indexed="true" stored="true"/>
203 <dynamicField name="*_txt" type="text_general" indexed="true" stored="true" multiValued="true"/>
204 <dynamicField name="*_en" type="text_en" indexed="true" stored="true" multiValued="true"/>
205 <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
206 <dynamicField name="*_bs" type="boolean" indexed="true" stored="true" multiValued="true"/>
207 <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
208 <dynamicField name="*_fs" type="float" indexed="true" stored="true" multiValued="true"/>
209 <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
210 <dynamicField name="*_ds" type="double" indexed="true" stored="true" multiValued="true"/>
212 <!-- Type used to index the lat and lon components for the "location" FieldType -->
213 <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false" />
215 <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
216 <dynamicField name="*_dts" type="date" indexed="true" stored="true" multiValued="true"/>
217 <dynamicField name="*_p" type="location" indexed="true" stored="true"/>
219 <!-- some trie-coded dynamic fields for faster range queries -->
220 <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
221 <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
222 <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
223 <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
224 <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
226 <dynamicField name="*_pi" type="pint" indexed="true" stored="true"/>
227 <!-- <dynamicField name="*_c" type="currency" indexed="true" stored="true"/>-->
229 <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
230 <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
232 <dynamicField name="random_*" type="random" />
234 <!-- uncomment the following to ignore any fields that don't already match an existing
235 field name or dynamic field, rather than reporting them as an error.
236 alternately, change the type="ignored" to some other type e.g. "text" if you want
237 unknown fields indexed and/or stored by default -->
238 <!--dynamicField name="*" type="ignored" multiValued="true" /-->
239 <field name="uid" type="string" indexed="true" stored="true"/>
243 <!-- Field to use to determine and enforce document uniqueness.
244 Unless this field is marked with required="false", it will be a required field
246 <uniqueKey>uid</uniqueKey>
248 <!-- DEPRECATED: The defaultSearchField is consulted by various query parsers when
249 parsing a query string that isn't explicit about the field. Machine (non-user)
250 generated queries are best made explicit, or they can use the "df" request parameter
251 which takes precedence over this.
252 Note: Un-commenting defaultSearchField will be insufficient if your request handler
253 in solrconfig.xml defines "df", which takes precedence. That would need to be removed.
254 <defaultSearchField>text</defaultSearchField> -->
256 <!-- DEPRECATED: The defaultOperator (AND|OR) is consulted by various query parsers
257 when parsing a query string to determine if a clause of the query should be marked as
258 required or optional, assuming the clause isn't already marked by some operator.
259 The default is OR, which is generally assumed so it is not a good idea to change it
260 globally here. The "q.op" request parameter takes precedence over this.
261 <solrQueryParser defaultOperator="OR"/> -->
263 <!-- copyField commands copy one field to another at the time a document
264 is added to the index. It's used either to index the same field differently,
265 or to add multiple fields to the same field for easier/faster searching. -->
267 <copyField source="themes" dest="themes_pl"/>
268 <copyField source="tag_name" dest="tag_name_pl"/>
271 <copyField source="cat" dest="text"/>
272 <copyField source="name" dest="text"/>
273 <copyField source="manu" dest="text"/>
274 <copyField source="features" dest="text"/>
275 <copyField source="includes" dest="text"/>
276 <copyField source="manu" dest="manu_exact"/>
278 <!-- Copy the price into a currency enabled field (default USD) -->
279 <!-- <copyField source="price" dest="price_c"/>-->
281 <!-- Text fields from SolrCell to search by default in our catch-all field -->
282 <!-- <copyField source="title" dest="text"/>
283 <copyField source="author" dest="text"/>
284 <copyField source="description" dest="text"/>
285 <copyField source="keywords" dest="text"/>
286 <copyField source="content" dest="text"/>
287 <copyField source="content_type" dest="text"/>
288 <copyField source="resourcename" dest="text"/>
289 <copyField source="url" dest="text"/>-->
291 <!-- Create a string version of author for faceting -->
292 <!-- <copyField source="author" dest="author_s"/>-->
294 <!-- Above, multiple source fields are copied to the [text] field.
295 Another way to map multiple source fields to the same
296 destination field is to use the dynamic field syntax.
297 copyField also supports a maxChars to copy setting. -->
299 <!-- <copyField source="*_t" dest="text" maxChars="3000"/> -->
301 <!-- copy name to alphaNameSort, a field designed for sorting by name -->
302 <!-- <copyField source="name" dest="alphaNameSort"/> -->
305 <!-- field type definitions. The "name" attribute is
306 just a label to be used by field definitions. The "class"
307 attribute and any other attributes determine the real
308 behavior of the fieldType.
309 Class names starting with "solr" refer to java classes in a
310 standard package such as org.apache.solr.analysis
313 <!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
314 <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
316 <!-- boolean type: "true" or "false" -->
317 <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
319 <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
320 currently supported on types that are sorted internally as strings
321 and on numeric types.
322 This includes "string","boolean", and, as of 3.5 (and 4.x),
323 int, float, long, date, double, including the "Trie" variants.
324 - If sortMissingLast="true", then a sort on this field will cause documents
325 without the field to come after documents with the field,
326 regardless of the requested sort order (asc or desc).
327 - If sortMissingFirst="true", then a sort on this field will cause documents
328 without the field to come before documents with the field,
329 regardless of the requested sort order.
330 - If sortMissingLast="false" and sortMissingFirst="false" (the default),
331 then default lucene sorting will be used which places docs without the
332 field first in an ascending sort and last in a descending sort.
336 Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
338 <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
339 <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
340 <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
341 <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
344 Numeric field types that index each value at various levels of precision
345 to accelerate range queries when the number of values between the range
346 endpoints is large. See the javadoc for NumericRangeQuery for internal
347 implementation details.
349 Smaller precisionStep values (specified in bits) will lead to more tokens
350 indexed per value, slightly larger index size, and faster range queries.
351 A precisionStep of 0 disables indexing at different precision levels.
353 <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
354 <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
355 <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
356 <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
358 <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
359 is a more restricted form of the canonical representation of dateTime
360 http://www.w3.org/TR/xmlschema-2/#dateTime
361 The trailing "Z" designates UTC time and is mandatory.
362 Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
363 All other components are mandatory.
365 Expressions can also be used to denote calculations that should be
366 performed relative to "NOW" to determine the value, ie...
369 ... Round to the start of the current hour
371 ... Exactly 1 day prior to now
372 NOW/DAY+6MONTHS+3DAYS
373 ... 6 months and 3 days in the future from the start of
376 Consult the DateField javadocs for more information.
378 Note: For faster range queries, consider the tdate type
380 <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
382 <!-- A Trie based date field for faster date range queries and date faceting. -->
383 <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
386 <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
387 <fieldtype name="binary" class="solr.BinaryField"/>
391 These should only be used for compatibility with existing indexes (created with lucene or older Solr versions).
392 Use Trie based fields instead. As of Solr 3.5 and 4.x, Trie based fields support sortMissingFirst/Last
394 Plain numeric field types that store and index the text
395 value verbatim (and hence don't correctly support range queries, since the
396 lexicographic ordering isn't equal to the numeric ordering)
398 <fieldType name="pint" class="solr.IntField"/>
399 <fieldType name="plong" class="solr.LongField"/>
400 <fieldType name="pfloat" class="solr.FloatField"/>
401 <fieldType name="pdouble" class="solr.DoubleField"/>
402 <fieldType name="pdate" class="solr.DateField" sortMissingLast="true"/>
404 <!-- The "RandomSortField" is not used to store or search any
405 data. You can declare fields of this type it in your schema
406 to generate pseudo-random orderings of your docs for sorting
407 or function purposes. The ordering is generated based on the field
408 name and the version of the index. As long as the index version
409 remains unchanged, and the same field name is reused,
410 the ordering of the docs will be consistent.
411 If you want different psuedo-random orderings of documents,
412 for the same version of the index, use a dynamicField and
413 change the field name in the request.
415 <fieldType name="random" class="solr.RandomSortField" indexed="true" />
417 <!-- solr.TextField allows the specification of custom text analyzers
418 specified as a tokenizer and a list of token filters. Different
419 analyzers may be specified for indexing and querying.
421 The optional positionIncrementGap puts space between multiple fields of
422 this type on the same document, with the purpose of preventing false phrase
423 matching across fields.
425 For more info on customizing your analyzer chain, please see
426 http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
429 <!-- One can also specify an existing Analyzer class that has a
430 default constructor via the class attribute on the analyzer element.
432 <fieldType name="text_greek" class="solr.TextField">
433 <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
437 <fieldType name="uuid" class="solr.UUIDField" indexed="true" />
440 <!-- A text field that only splits on whitespace for exact matching of words -->
441 <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
443 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
447 <!-- A general text field that has reasonable, generic
448 cross-language defaults: it tokenizes with StandardTokenizer,
449 removes stop words from case-insensitive "stopwords.txt"
450 (empty by default), and down cases. At query time only, it
451 also applies synonyms. -->
452 <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
453 <analyzer type="index">
454 <tokenizer class="solr.StandardTokenizerFactory"/>
455 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
456 <!-- in this example, we will only use synonyms at query time
457 <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
459 <filter class="solr.LowerCaseFilterFactory"/>
461 <analyzer type="query">
462 <tokenizer class="solr.StandardTokenizerFactory"/>
463 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
464 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
465 <filter class="solr.LowerCaseFilterFactory"/>
469 <!-- A text field with defaults appropriate for English: it
470 tokenizes with StandardTokenizer, removes English stop words
471 (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
472 finally applies Porter's stemming. The query time analyzer
473 also applies synonyms from synonyms.txt. -->
474 <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
475 <analyzer type="index">
476 <tokenizer class="solr.StandardTokenizerFactory"/>
477 <!-- in this example, we will only use synonyms at query time
478 <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
480 <!-- Case insensitive stop word removal.
481 add enablePositionIncrements=true in both the index and query
482 analyzers to leave a 'gap' for more accurate phrase queries.
484 <filter class="solr.StopFilterFactory"
486 words="lang/stopwords_en.txt"
487 enablePositionIncrements="true"
489 <filter class="solr.LowerCaseFilterFactory"/>
490 <filter class="solr.EnglishPossessiveFilterFactory"/>
491 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
492 <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
493 <filter class="solr.EnglishMinimalStemFilterFactory"/>
495 <filter class="solr.PorterStemFilterFactory"/>
497 <analyzer type="query">
498 <tokenizer class="solr.StandardTokenizerFactory"/>
499 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
500 <filter class="solr.StopFilterFactory"
502 words="lang/stopwords_en.txt"
503 enablePositionIncrements="true"
505 <filter class="solr.LowerCaseFilterFactory"/>
506 <filter class="solr.EnglishPossessiveFilterFactory"/>
507 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
508 <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
509 <filter class="solr.EnglishMinimalStemFilterFactory"/>
511 <filter class="solr.PorterStemFilterFactory"/>
515 <!-- A text field with defaults appropriate for English, plus
516 aggressive word-splitting and autophrase features enabled.
517 This field is just like text_en, except it adds
518 WordDelimiterFilter to enable splitting and matching of
519 words on case-change, alpha numeric boundaries, and
520 non-alphanumeric chars. This means certain compound word
521 cases will work, for example query "wi fi" will match
522 document "WiFi" or "wi-fi".
524 <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
525 <analyzer type="index">
526 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
527 <!-- in this example, we will only use synonyms at query time
528 <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
530 <!-- Case insensitive stop word removal.
531 add enablePositionIncrements=true in both the index and query
532 analyzers to leave a 'gap' for more accurate phrase queries.
534 <filter class="solr.StopFilterFactory"
536 words="lang/stopwords_en.txt"
537 enablePositionIncrements="true"
539 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
540 <filter class="solr.LowerCaseFilterFactory"/>
541 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
542 <filter class="solr.PorterStemFilterFactory"/>
544 <analyzer type="query">
545 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
546 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
547 <filter class="solr.StopFilterFactory"
549 words="lang/stopwords_en.txt"
550 enablePositionIncrements="true"
552 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
553 <filter class="solr.LowerCaseFilterFactory"/>
554 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
555 <filter class="solr.PorterStemFilterFactory"/>
559 <!-- Less flexible matching, but less false matches. Probably not ideal for product names,
560 but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
561 <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
563 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
564 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
565 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
566 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
567 <filter class="solr.LowerCaseFilterFactory"/>
568 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
569 <filter class="solr.EnglishMinimalStemFilterFactory"/>
570 <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
571 possible with WordDelimiterFilter in conjuncton with stemming. -->
572 <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
576 <!-- Just like text_general except it reverses the characters of
577 each token, to enable more efficient leading wildcard queries. -->
578 <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
579 <analyzer type="index">
580 <tokenizer class="solr.StandardTokenizerFactory"/>
581 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
582 <filter class="solr.LowerCaseFilterFactory"/>
583 <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
584 maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
586 <analyzer type="query">
587 <tokenizer class="solr.StandardTokenizerFactory"/>
588 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
589 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
590 <filter class="solr.LowerCaseFilterFactory"/>
594 <!-- charFilter + WhitespaceTokenizer -->
596 <fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
598 <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
599 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
604 <!-- This is an example of using the KeywordTokenizer along
605 With various TokenFilterFactories to produce a sortable field
606 that does not include some properties of the source text
608 <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
610 <!-- KeywordTokenizer does no actual tokenizing, so the entire
611 input string is preserved as a single token
613 <tokenizer class="solr.KeywordTokenizerFactory"/>
614 <!-- The LowerCase TokenFilter does what you expect, which can be
615 when you want your sorting to be case insensitive
617 <filter class="solr.LowerCaseFilterFactory" />
618 <!-- The TrimFilter removes any leading or trailing whitespace -->
619 <filter class="solr.TrimFilterFactory" />
620 <!-- The PatternReplaceFilter gives you the flexibility to use
621 Java Regular expression to replace any sequence of characters
622 matching a pattern with an arbitrary replacement string,
623 which may include back references to portions of the original
624 string matched by the pattern.
626 See the Java Regular Expression documentation for more
627 information on pattern and replacement string syntax.
629 http://java.sun.com/j2se/1.6.0/docs/api/java/util/regex/package-summary.html
631 <filter class="solr.PatternReplaceFilterFactory"
632 pattern="([^a-z])" replacement="" replace="all"
637 <fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
639 <tokenizer class="solr.StandardTokenizerFactory"/>
640 <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
644 <fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
646 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
648 The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
649 a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
650 Attributes of the DelimitedPayloadTokenFilterFactory :
651 "delimiter" - a one character delimiter. Default is | (pipe)
652 "encoder" - how to encode the following value into a playload
653 float -> org.apache.lucene.analysis.payloads.FloatEncoder,
654 integer -> o.a.l.a.p.IntegerEncoder
655 identity -> o.a.l.a.p.IdentityEncoder
656 Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
658 <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
662 <!-- lowercases the entire field value, keeping it as a single token. -->
663 <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
665 <tokenizer class="solr.KeywordTokenizerFactory"/>
666 <filter class="solr.LowerCaseFilterFactory" />
671 Example of using PathHierarchyTokenizerFactory at index time, so
672 queries for paths match documents at that path, or in descendent paths
674 <fieldType name="descendent_path" class="solr.TextField">
675 <analyzer type="index">
676 <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
678 <analyzer type="query">
679 <tokenizer class="solr.KeywordTokenizerFactory" />
683 Example of using PathHierarchyTokenizerFactory at query time, so
684 queries for paths match documents at that path, or in ancestor paths
686 <fieldType name="ancestor_path" class="solr.TextField">
687 <analyzer type="index">
688 <tokenizer class="solr.KeywordTokenizerFactory" />
690 <analyzer type="query">
691 <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
695 <!-- since fields of this type are by default not stored or indexed,
696 any data added to them will be ignored outright. -->
697 <fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
699 <!-- This point type indexes the coordinates as separate fields (subFields)
700 If subFieldType is defined, it references a type, and a dynamic field
701 definition is created matching *___<typename>. Alternately, if
702 subFieldSuffix is defined, that is used to create the subFields.
703 Example: if subFieldType="double", then the coordinates would be
704 indexed in fields myloc_0___double,myloc_1___double.
705 Example: if subFieldSuffix="_d" then the coordinates would be indexed
706 in fields myloc_0_d,myloc_1_d
707 The subFields are an implementation detail of the fieldType, and end
708 users normally should not need to know about them.
710 <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
712 <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
713 <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
716 A Geohash is a compact representation of a latitude longitude pair in a single field.
717 See http://wiki.apache.org/solr/SpatialSearch
719 <fieldtype name="geohash" class="solr.GeoHashField"/>
721 <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
723 defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
724 precisionStep: Specifies the precisionStep for the TrieLong field used for the amount
725 providerClass: Lets you plug in other exchange provider backend:
726 solr.FileExchangeRateProvider is the default and takes one parameter:
727 currencyConfig: name of an xml file holding exhange rates
728 solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
729 ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
730 refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
732 <!-- <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" /> - nie dziala -->
736 <!-- some examples for different languages (generally ordered by ISO code) -->
739 <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
741 <tokenizer class="solr.StandardTokenizerFactory"/>
742 <!-- for any non-arabic -->
743 <filter class="solr.LowerCaseFilterFactory"/>
744 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" enablePositionIncrements="true"/>
745 <!-- normalizes ﻯ to ﻱ, etc -->
746 <filter class="solr.ArabicNormalizationFilterFactory"/>
747 <filter class="solr.ArabicStemFilterFactory"/>
752 <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
754 <tokenizer class="solr.StandardTokenizerFactory"/>
755 <filter class="solr.LowerCaseFilterFactory"/>
756 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" enablePositionIncrements="true"/>
757 <filter class="solr.BulgarianStemFilterFactory"/>
762 <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
764 <tokenizer class="solr.StandardTokenizerFactory"/>
765 <!-- removes l', etc -->
766 <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
767 <filter class="solr.LowerCaseFilterFactory"/>
768 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" enablePositionIncrements="true"/>
769 <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
773 <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
774 <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
776 <tokenizer class="solr.StandardTokenizerFactory"/>
777 <!-- normalize width before bigram, as e.g. half-width dakuten combine -->
778 <filter class="solr.CJKWidthFilterFactory"/>
779 <!-- for any non-CJK -->
780 <filter class="solr.LowerCaseFilterFactory"/>
781 <filter class="solr.CJKBigramFilterFactory"/>
786 <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
788 <tokenizer class="solr.StandardTokenizerFactory"/>
789 <filter class="solr.LowerCaseFilterFactory"/>
790 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" enablePositionIncrements="true"/>
791 <filter class="solr.CzechStemFilterFactory"/>
796 <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
798 <tokenizer class="solr.StandardTokenizerFactory"/>
799 <filter class="solr.LowerCaseFilterFactory"/>
800 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" enablePositionIncrements="true"/>
801 <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
806 <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
808 <tokenizer class="solr.StandardTokenizerFactory"/>
809 <filter class="solr.LowerCaseFilterFactory"/>
810 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" enablePositionIncrements="true"/>
811 <filter class="solr.GermanNormalizationFilterFactory"/>
812 <filter class="solr.GermanLightStemFilterFactory"/>
813 <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
814 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
819 <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
821 <tokenizer class="solr.StandardTokenizerFactory"/>
822 <!-- greek specific lowercase for sigma -->
823 <filter class="solr.GreekLowerCaseFilterFactory"/>
824 <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" enablePositionIncrements="true"/>
825 <filter class="solr.GreekStemFilterFactory"/>
830 <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
832 <tokenizer class="solr.StandardTokenizerFactory"/>
833 <filter class="solr.LowerCaseFilterFactory"/>
834 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" enablePositionIncrements="true"/>
835 <filter class="solr.SpanishLightStemFilterFactory"/>
836 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
841 <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
843 <tokenizer class="solr.StandardTokenizerFactory"/>
844 <filter class="solr.LowerCaseFilterFactory"/>
845 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" enablePositionIncrements="true"/>
846 <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
851 <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
854 <charFilter class="solr.PersianCharFilterFactory"/>
855 <tokenizer class="solr.StandardTokenizerFactory"/>
856 <filter class="solr.LowerCaseFilterFactory"/>
857 <filter class="solr.ArabicNormalizationFilterFactory"/>
858 <filter class="solr.PersianNormalizationFilterFactory"/>
859 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" enablePositionIncrements="true"/>
864 <fieldType name="text_fi" 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_fi.txt" format="snowball" enablePositionIncrements="true"/>
869 <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
870 <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
875 <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
877 <tokenizer class="solr.StandardTokenizerFactory"/>
878 <!-- removes l', etc -->
879 <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
880 <filter class="solr.LowerCaseFilterFactory"/>
881 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" enablePositionIncrements="true"/>
882 <filter class="solr.FrenchLightStemFilterFactory"/>
883 <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
884 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
889 <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
891 <tokenizer class="solr.StandardTokenizerFactory"/>
892 <!-- removes d', etc -->
893 <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
894 <!-- removes n-, etc. position increments is intentionally false! -->
895 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt" enablePositionIncrements="false"/>
896 <filter class="solr.IrishLowerCaseFilterFactory"/>
897 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt" enablePositionIncrements="true"/>
898 <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
903 <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
905 <tokenizer class="solr.StandardTokenizerFactory"/>
906 <filter class="solr.LowerCaseFilterFactory"/>
907 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" enablePositionIncrements="true"/>
908 <filter class="solr.GalicianStemFilterFactory"/>
909 <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
914 <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
916 <tokenizer class="solr.StandardTokenizerFactory"/>
917 <filter class="solr.LowerCaseFilterFactory"/>
918 <!-- normalizes unicode representation -->
919 <filter class="solr.IndicNormalizationFilterFactory"/>
920 <!-- normalizes variation in spelling -->
921 <filter class="solr.HindiNormalizationFilterFactory"/>
922 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" enablePositionIncrements="true"/>
923 <filter class="solr.HindiStemFilterFactory"/>
928 <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
930 <tokenizer class="solr.StandardTokenizerFactory"/>
931 <filter class="solr.LowerCaseFilterFactory"/>
932 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" enablePositionIncrements="true"/>
933 <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
934 <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
939 <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
941 <tokenizer class="solr.StandardTokenizerFactory"/>
942 <filter class="solr.LowerCaseFilterFactory"/>
943 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" enablePositionIncrements="true"/>
944 <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
949 <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
951 <tokenizer class="solr.StandardTokenizerFactory"/>
952 <filter class="solr.LowerCaseFilterFactory"/>
953 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" enablePositionIncrements="true"/>
954 <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
955 <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
960 <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
962 <tokenizer class="solr.StandardTokenizerFactory"/>
963 <!-- removes l', etc -->
964 <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
965 <filter class="solr.LowerCaseFilterFactory"/>
966 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" enablePositionIncrements="true"/>
967 <filter class="solr.ItalianLightStemFilterFactory"/>
968 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
972 <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
974 NOTE: If you want to optimize search for precision, use default operator AND in your query
975 parser config with <solrQueryParser defaultOperator="AND"/> further down in this file. Use
976 OR if you would like to optimize for recall (default).
978 <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
980 <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
982 Kuromoji has a search mode (default) that does segmentation useful for search. A heuristic
983 is used to segment compounds into its parts and the compound itself is kept as synonym.
985 Valid values for attribute mode are:
986 normal: regular segmentation
987 search: segmentation useful for search with synonyms compounds (default)
988 extended: same as search mode, but unigrams unknown words (experimental)
990 For some applications it might be good to use search mode for indexing and normal mode for
991 queries to reduce recall and prevent parts of compounds from being matched and highlighted.
992 Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
994 Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
995 model with your own entries for segmentation, part-of-speech tags and readings without a need
996 to specify weights. Notice that user dictionaries have not been subject to extensive testing.
998 User dictionary attributes are:
999 userDictionary: user dictionary filename
1000 userDictionaryEncoding: user dictionary encoding (default is UTF-8)
1002 See lang/userdict_ja.txt for a sample user dictionary file.
1004 Punctuation characters are discarded by default. Use discardPunctuation="false" to keep them.
1006 See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
1008 <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
1009 <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
1010 <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
1011 <filter class="solr.JapaneseBaseFormFilterFactory"/>
1012 <!-- Removes tokens with certain part-of-speech tags -->
1013 <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" enablePositionIncrements="true"/>
1014 <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
1015 <filter class="solr.CJKWidthFilterFactory"/>
1016 <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
1017 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" enablePositionIncrements="true" />
1018 <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
1019 <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
1020 <!-- Lower-cases romaji characters -->
1021 <filter class="solr.LowerCaseFilterFactory"/>
1026 <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
1028 <tokenizer class="solr.StandardTokenizerFactory"/>
1029 <filter class="solr.LowerCaseFilterFactory"/>
1030 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" enablePositionIncrements="true"/>
1031 <filter class="solr.LatvianStemFilterFactory"/>
1036 <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
1038 <tokenizer class="solr.StandardTokenizerFactory"/>
1039 <filter class="solr.LowerCaseFilterFactory"/>
1040 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" enablePositionIncrements="true"/>
1041 <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
1042 <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
1047 <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
1049 <tokenizer class="solr.StandardTokenizerFactory"/>
1050 <filter class="solr.LowerCaseFilterFactory"/>
1051 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" enablePositionIncrements="true"/>
1052 <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
1053 <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> -->
1054 <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
1059 <fieldType name="text_pl" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
1061 <tokenizer class="solr.StandardTokenizerFactory"/>
1062 <filter class="solr.LowerCaseFilterFactory"/>
1063 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pl.txt" format="snowball" enablePositionIncrements="true"/>
1064 <filter class="solr.MorfologikFilterFactory" dictionary="MORFOLOGIK" />
1065 <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
1066 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
1067 <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
1073 <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
1075 <tokenizer class="solr.StandardTokenizerFactory"/>
1076 <filter class="solr.LowerCaseFilterFactory"/>
1077 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" enablePositionIncrements="true"/>
1078 <filter class="solr.PortugueseLightStemFilterFactory"/>
1079 <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
1080 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
1081 <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
1086 <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
1088 <tokenizer class="solr.StandardTokenizerFactory"/>
1089 <filter class="solr.LowerCaseFilterFactory"/>
1090 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" enablePositionIncrements="true"/>
1091 <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
1096 <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
1098 <tokenizer class="solr.StandardTokenizerFactory"/>
1099 <filter class="solr.LowerCaseFilterFactory"/>
1100 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" enablePositionIncrements="true"/>
1101 <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
1102 <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
1107 <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
1109 <tokenizer class="solr.StandardTokenizerFactory"/>
1110 <filter class="solr.LowerCaseFilterFactory"/>
1111 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" enablePositionIncrements="true"/>
1112 <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
1113 <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
1118 <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
1120 <tokenizer class="solr.StandardTokenizerFactory"/>
1121 <filter class="solr.LowerCaseFilterFactory"/>
1122 <filter class="solr.ThaiWordFilterFactory"/>
1123 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" enablePositionIncrements="true"/>
1128 <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
1130 <tokenizer class="solr.StandardTokenizerFactory"/>
1131 <filter class="solr.TurkishLowerCaseFilterFactory"/>
1132 <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" enablePositionIncrements="true"/>
1133 <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
1139 <!-- Similarity is the scoring routine for each document vs. a query.
1140 A custom Similarity or SimilarityFactory may be specified here, but
1141 the default is fine for most applications.
1142 For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
1145 <similarity class="com.example.solr.CustomSimilarityFactory">
1146 <str name="paramkey">param value</str>