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="lowercase" stored="false" indexed="true" omitNorms="true"/> <!-- no norms -->
133 <field name="is_book" type="boolean" stored="false" indexed="true"/>
134 <field name="authors" type="text_pl_nonstop" stored="false" indexed="true" multiValued="true" termPositions="true" termVectors="true"/>
135 <field name="translators" type="text_pl_nonstop" stored="false" indexed="false" multiValued="true" />
136 <field name="title" type="text_pl_nonstop" stored="false" indexed="true"/>
137 <!-- <field name="published_date" type="tdate" stored="false" indexed="true"/>-->
138 <field name="published_date" type="string" stored="true" indexed="true"/>
140 <field name="epochs" type="lowercase" stored="false" indexed="false" multiValued="true" />
141 <field name="kinds" type="lowercase" stored="false" indexed="false" multiValued="true" />
142 <field name="genres" type="lowercase" stored="false" indexed="false" multiValued="true" />
144 <field name="metadata" type="text_pl_nonstop" stored="false" indexed="true" multiValued="true" termPositions="true" termVectors="true" />
146 <field name="themes" type="lowercase" stored="true" indexed="true" termVectors="true" termPositions="true" multiValued="true" />
147 <field name="themes_pl" type="text_pl_nonstop" stored="true" indexed="true" termVectors="true" termPositions="true" multiValued="true" />
148 <field name="header_index" type="int" stored="true" indexed="true"/>
149 <field name="header_span" type="int" stored="true" indexed="true"/>
150 <field name="header_type" type="lowercase" stored="true" indexed="false"/>
151 <field name="text" type="text_pl" stored="false" indexed="true" termVectors="true" termPositions="true" />
153 <field name="snippets_position" type="int" stored="true" indexed="false"/>
154 <field name="snippets_length" type="int" stored="true" indexed="false"/>
155 <field name="snippets_revision" type="int" stored="true" indexed="false"/>
156 <field name="fragment_anchor" type="string" stored="true" indexed="false"/>
158 <field name="tag_id" type="int" stored="true" indexed="true"/>
159 <field name="tag_name" type="lowercase" stored="true" indexed="true" />
160 <field name="tag_name_pl" type="text_pl_nonstop" stored="false" indexed="true" multiValued="true"/>
161 <field name="tag_category" type="string" stored="true" indexed="true" />
162 <field name="is_pdcounter" type="boolean" stored="true" indexed="true" />
164 <!-- Main body of document extracted by SolrCell.
165 NOTE: This field is not indexed by default, since it is also copied to "text"
166 using copyField below. This is to save space. Use this field for returning and
167 highlighting document content. Use the "text" field to search the content. -->
168 <!-- <field name="content" type="text_general" indexed="false" stored="true" multiValued="true"/> -->
171 <!-- catchall field, containing all other searchable text fields (implemented
172 via copyField further on in this schema -->
173 <!-- <field name="text" type="text_general" indexed="true" stored="false" multiValued="true"/> -->
175 <!-- catchall text field that indexes tokens both normally and in reverse for efficient
176 leading wildcard queries. -->
177 <!-- <field name="text_rev" type="text_general_rev" indexed="true" stored="false" multiValued="true"/> -->
179 <!-- non-tokenized version of manufacturer to make it easier to sort or group
180 results by manufacturer. copied from "manu" via copyField -->
181 <!-- <field name="manu_exact" type="string" indexed="true" stored="false"/> -->
183 <!-- <field name="payloads" type="payloads" indexed="true" stored="true"/> -->
185 <field name="_version_" type="long" indexed="true" stored="true"/>
187 <!-- Uncommenting the following will create a "timestamp" field using
188 a default value of "NOW" to indicate when each document was indexed.
191 <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
194 <!-- Dynamic field definitions allow using convention over configuration
195 for fields via the specification of patterns to match field names.
196 EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
197 RESTRICTION: the glob-like pattern in the name attribute must have
198 a "*" only at the start or the end. -->
200 <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
201 <dynamicField name="*_is" type="int" indexed="true" stored="true" multiValued="true"/>
202 <dynamicField name="*_s" type="string" indexed="true" stored="true" />
203 <dynamicField name="*_ss" type="string" indexed="true" stored="true" multiValued="true"/>
204 <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
205 <dynamicField name="*_ls" type="long" indexed="true" stored="true" multiValued="true"/>
206 <dynamicField name="*_t" type="text_general" indexed="true" stored="true"/>
207 <dynamicField name="*_txt" type="text_general" indexed="true" stored="true" multiValued="true"/>
208 <dynamicField name="*_en" type="text_en" indexed="true" stored="true" multiValued="true"/>
209 <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
210 <dynamicField name="*_bs" type="boolean" indexed="true" stored="true" multiValued="true"/>
211 <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
212 <dynamicField name="*_fs" type="float" indexed="true" stored="true" multiValued="true"/>
213 <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
214 <dynamicField name="*_ds" type="double" indexed="true" stored="true" multiValued="true"/>
216 <!-- Type used to index the lat and lon components for the "location" FieldType -->
217 <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false" />
219 <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
220 <dynamicField name="*_dts" type="date" indexed="true" stored="true" multiValued="true"/>
221 <dynamicField name="*_p" type="location" indexed="true" stored="true"/>
223 <!-- some trie-coded dynamic fields for faster range queries -->
224 <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
225 <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
226 <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
227 <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
228 <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
230 <dynamicField name="*_pi" type="pint" indexed="true" stored="true"/>
231 <!-- <dynamicField name="*_c" type="currency" indexed="true" stored="true"/>-->
233 <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
234 <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
236 <dynamicField name="random_*" type="random" />
238 <!-- uncomment the following to ignore any fields that don't already match an existing
239 field name or dynamic field, rather than reporting them as an error.
240 alternately, change the type="ignored" to some other type e.g. "text" if you want
241 unknown fields indexed and/or stored by default -->
242 <!--dynamicField name="*" type="ignored" multiValued="true" /-->
243 <field name="uid" type="string" indexed="true" stored="true"/>
247 <!-- Field to use to determine and enforce document uniqueness.
248 Unless this field is marked with required="false", it will be a required field
250 <uniqueKey>uid</uniqueKey>
252 <!-- DEPRECATED: The defaultSearchField is consulted by various query parsers when
253 parsing a query string that isn't explicit about the field. Machine (non-user)
254 generated queries are best made explicit, or they can use the "df" request parameter
255 which takes precedence over this.
256 Note: Un-commenting defaultSearchField will be insufficient if your request handler
257 in solrconfig.xml defines "df", which takes precedence. That would need to be removed.
258 <defaultSearchField>text</defaultSearchField> -->
260 <!-- DEPRECATED: The defaultOperator (AND|OR) is consulted by various query parsers
261 when parsing a query string to determine if a clause of the query should be marked as
262 required or optional, assuming the clause isn't already marked by some operator.
263 The default is OR, which is generally assumed so it is not a good idea to change it
264 globally here. The "q.op" request parameter takes precedence over this.
265 <solrQueryParser defaultOperator="OR"/> -->
267 <!-- copyField commands copy one field to another at the time a document
268 is added to the index. It's used either to index the same field differently,
269 or to add multiple fields to the same field for easier/faster searching. -->
271 <copyField source="themes" dest="themes_pl"/>
272 <copyField source="tag_name" dest="tag_name_pl"/>
274 <copyField source="translators" dest="metadata"/>
275 <copyField source="epochs" dest="metadata"/>
276 <copyField source="kinds" dest="metadata"/>
277 <copyField source="genres" dest="metadata"/>
280 <copyField source="cat" dest="text"/>
281 <copyField source="name" dest="text"/>
282 <copyField source="manu" dest="text"/>
283 <copyField source="features" dest="text"/>
284 <copyField source="includes" dest="text"/>
285 <copyField source="manu" dest="manu_exact"/>
287 <!-- Copy the price into a currency enabled field (default USD) -->
288 <!-- <copyField source="price" dest="price_c"/>-->
290 <!-- Text fields from SolrCell to search by default in our catch-all field -->
291 <!-- <copyField source="title" dest="text"/>
292 <copyField source="author" dest="text"/>
293 <copyField source="description" dest="text"/>
294 <copyField source="keywords" dest="text"/>
295 <copyField source="content" dest="text"/>
296 <copyField source="content_type" dest="text"/>
297 <copyField source="resourcename" dest="text"/>
298 <copyField source="url" dest="text"/>-->
300 <!-- Create a string version of author for faceting -->
301 <!-- <copyField source="author" dest="author_s"/>-->
303 <!-- Above, multiple source fields are copied to the [text] field.
304 Another way to map multiple source fields to the same
305 destination field is to use the dynamic field syntax.
306 copyField also supports a maxChars to copy setting. -->
308 <!-- <copyField source="*_t" dest="text" maxChars="3000"/> -->
310 <!-- copy name to alphaNameSort, a field designed for sorting by name -->
311 <!-- <copyField source="name" dest="alphaNameSort"/> -->
314 <!-- field type definitions. The "name" attribute is
315 just a label to be used by field definitions. The "class"
316 attribute and any other attributes determine the real
317 behavior of the fieldType.
318 Class names starting with "solr" refer to java classes in a
319 standard package such as org.apache.solr.analysis
322 <!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
323 <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
325 <!-- boolean type: "true" or "false" -->
326 <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
328 <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
329 currently supported on types that are sorted internally as strings
330 and on numeric types.
331 This includes "string","boolean", and, as of 3.5 (and 4.x),
332 int, float, long, date, double, including the "Trie" variants.
333 - If sortMissingLast="true", then a sort on this field will cause documents
334 without the field to come after documents with the field,
335 regardless of the requested sort order (asc or desc).
336 - If sortMissingFirst="true", then a sort on this field will cause documents
337 without the field to come before documents with the field,
338 regardless of the requested sort order.
339 - If sortMissingLast="false" and sortMissingFirst="false" (the default),
340 then default lucene sorting will be used which places docs without the
341 field first in an ascending sort and last in a descending sort.
345 Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
347 <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
348 <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
349 <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
350 <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
353 Numeric field types that index each value at various levels of precision
354 to accelerate range queries when the number of values between the range
355 endpoints is large. See the javadoc for NumericRangeQuery for internal
356 implementation details.
358 Smaller precisionStep values (specified in bits) will lead to more tokens
359 indexed per value, slightly larger index size, and faster range queries.
360 A precisionStep of 0 disables indexing at different precision levels.
362 <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
363 <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
364 <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
365 <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
367 <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
368 is a more restricted form of the canonical representation of dateTime
369 http://www.w3.org/TR/xmlschema-2/#dateTime
370 The trailing "Z" designates UTC time and is mandatory.
371 Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
372 All other components are mandatory.
374 Expressions can also be used to denote calculations that should be
375 performed relative to "NOW" to determine the value, ie...
378 ... Round to the start of the current hour
380 ... Exactly 1 day prior to now
381 NOW/DAY+6MONTHS+3DAYS
382 ... 6 months and 3 days in the future from the start of
385 Consult the DateField javadocs for more information.
387 Note: For faster range queries, consider the tdate type
389 <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
391 <!-- A Trie based date field for faster date range queries and date faceting. -->
392 <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
395 <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
396 <fieldtype name="binary" class="solr.BinaryField"/>
400 These should only be used for compatibility with existing indexes (created with lucene or older Solr versions).
401 Use Trie based fields instead. As of Solr 3.5 and 4.x, Trie based fields support sortMissingFirst/Last
403 Plain numeric field types that store and index the text
404 value verbatim (and hence don't correctly support range queries, since the
405 lexicographic ordering isn't equal to the numeric ordering)
407 <fieldType name="pint" class="solr.IntField"/>
408 <fieldType name="plong" class="solr.LongField"/>
409 <fieldType name="pfloat" class="solr.FloatField"/>
410 <fieldType name="pdouble" class="solr.DoubleField"/>
411 <fieldType name="pdate" class="solr.DateField" sortMissingLast="true"/>
413 <!-- The "RandomSortField" is not used to store or search any
414 data. You can declare fields of this type it in your schema
415 to generate pseudo-random orderings of your docs for sorting
416 or function purposes. The ordering is generated based on the field
417 name and the version of the index. As long as the index version
418 remains unchanged, and the same field name is reused,
419 the ordering of the docs will be consistent.
420 If you want different psuedo-random orderings of documents,
421 for the same version of the index, use a dynamicField and
422 change the field name in the request.
424 <fieldType name="random" class="solr.RandomSortField" indexed="true" />
426 <!-- solr.TextField allows the specification of custom text analyzers
427 specified as a tokenizer and a list of token filters. Different
428 analyzers may be specified for indexing and querying.
430 The optional positionIncrementGap puts space between multiple fields of
431 this type on the same document, with the purpose of preventing false phrase
432 matching across fields.
434 For more info on customizing your analyzer chain, please see
435 http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
438 <!-- One can also specify an existing Analyzer class that has a
439 default constructor via the class attribute on the analyzer element.
441 <fieldType name="text_greek" class="solr.TextField">
442 <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
446 <fieldType name="uuid" class="solr.UUIDField" indexed="true" />
449 <!-- A text field that only splits on whitespace for exact matching of words -->
450 <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
452 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
456 <!-- A general text field that has reasonable, generic
457 cross-language defaults: it tokenizes with StandardTokenizer,
458 removes stop words from case-insensitive "stopwords.txt"
459 (empty by default), and down cases. At query time only, it
460 also applies synonyms. -->
461 <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
462 <analyzer type="index">
463 <tokenizer class="solr.StandardTokenizerFactory"/>
464 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
465 <!-- in this example, we will only use synonyms at query time
466 <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
468 <filter class="solr.LowerCaseFilterFactory"/>
470 <analyzer type="query">
471 <tokenizer class="solr.StandardTokenizerFactory"/>
472 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
473 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
474 <filter class="solr.LowerCaseFilterFactory"/>
478 <!-- A text field with defaults appropriate for English: it
479 tokenizes with StandardTokenizer, removes English stop words
480 (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
481 finally applies Porter's stemming. The query time analyzer
482 also applies synonyms from synonyms.txt. -->
483 <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
484 <analyzer type="index">
485 <tokenizer class="solr.StandardTokenizerFactory"/>
486 <!-- in this example, we will only use synonyms at query time
487 <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
489 <!-- Case insensitive stop word removal.
490 add enablePositionIncrements=true in both the index and query
491 analyzers to leave a 'gap' for more accurate phrase queries.
493 <filter class="solr.StopFilterFactory"
495 words="lang/stopwords_en.txt"
496 enablePositionIncrements="true"
498 <filter class="solr.LowerCaseFilterFactory"/>
499 <filter class="solr.EnglishPossessiveFilterFactory"/>
500 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
501 <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
502 <filter class="solr.EnglishMinimalStemFilterFactory"/>
504 <filter class="solr.PorterStemFilterFactory"/>
506 <analyzer type="query">
507 <tokenizer class="solr.StandardTokenizerFactory"/>
508 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
509 <filter class="solr.StopFilterFactory"
511 words="lang/stopwords_en.txt"
512 enablePositionIncrements="true"
514 <filter class="solr.LowerCaseFilterFactory"/>
515 <filter class="solr.EnglishPossessiveFilterFactory"/>
516 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
517 <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
518 <filter class="solr.EnglishMinimalStemFilterFactory"/>
520 <filter class="solr.PorterStemFilterFactory"/>
524 <!-- A text field with defaults appropriate for English, plus
525 aggressive word-splitting and autophrase features enabled.
526 This field is just like text_en, except it adds
527 WordDelimiterFilter to enable splitting and matching of
528 words on case-change, alpha numeric boundaries, and
529 non-alphanumeric chars. This means certain compound word
530 cases will work, for example query "wi fi" will match
531 document "WiFi" or "wi-fi".
533 <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
534 <analyzer type="index">
535 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
536 <!-- in this example, we will only use synonyms at query time
537 <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
539 <!-- Case insensitive stop word removal.
540 add enablePositionIncrements=true in both the index and query
541 analyzers to leave a 'gap' for more accurate phrase queries.
543 <filter class="solr.StopFilterFactory"
545 words="lang/stopwords_en.txt"
546 enablePositionIncrements="true"
548 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
549 <filter class="solr.LowerCaseFilterFactory"/>
550 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
551 <filter class="solr.PorterStemFilterFactory"/>
553 <analyzer type="query">
554 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
555 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
556 <filter class="solr.StopFilterFactory"
558 words="lang/stopwords_en.txt"
559 enablePositionIncrements="true"
561 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
562 <filter class="solr.LowerCaseFilterFactory"/>
563 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
564 <filter class="solr.PorterStemFilterFactory"/>
568 <!-- Less flexible matching, but less false matches. Probably not ideal for product names,
569 but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
570 <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
572 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
573 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
574 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
575 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
576 <filter class="solr.LowerCaseFilterFactory"/>
577 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
578 <filter class="solr.EnglishMinimalStemFilterFactory"/>
579 <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
580 possible with WordDelimiterFilter in conjuncton with stemming. -->
581 <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
585 <!-- Just like text_general except it reverses the characters of
586 each token, to enable more efficient leading wildcard queries. -->
587 <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
588 <analyzer type="index">
589 <tokenizer class="solr.StandardTokenizerFactory"/>
590 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
591 <filter class="solr.LowerCaseFilterFactory"/>
592 <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
593 maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
595 <analyzer type="query">
596 <tokenizer class="solr.StandardTokenizerFactory"/>
597 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
598 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
599 <filter class="solr.LowerCaseFilterFactory"/>
603 <!-- charFilter + WhitespaceTokenizer -->
605 <fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
607 <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
608 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
613 <!-- This is an example of using the KeywordTokenizer along
614 With various TokenFilterFactories to produce a sortable field
615 that does not include some properties of the source text
617 <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
619 <!-- KeywordTokenizer does no actual tokenizing, so the entire
620 input string is preserved as a single token
622 <tokenizer class="solr.KeywordTokenizerFactory"/>
623 <!-- The LowerCase TokenFilter does what you expect, which can be
624 when you want your sorting to be case insensitive
626 <filter class="solr.LowerCaseFilterFactory" />
627 <!-- The TrimFilter removes any leading or trailing whitespace -->
628 <filter class="solr.TrimFilterFactory" />
629 <!-- The PatternReplaceFilter gives you the flexibility to use
630 Java Regular expression to replace any sequence of characters
631 matching a pattern with an arbitrary replacement string,
632 which may include back references to portions of the original
633 string matched by the pattern.
635 See the Java Regular Expression documentation for more
636 information on pattern and replacement string syntax.
638 http://java.sun.com/j2se/1.6.0/docs/api/java/util/regex/package-summary.html
640 <filter class="solr.PatternReplaceFilterFactory"
641 pattern="([^a-z])" replacement="" replace="all"
646 <fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
648 <tokenizer class="solr.StandardTokenizerFactory"/>
649 <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
653 <fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
655 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
657 The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
658 a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
659 Attributes of the DelimitedPayloadTokenFilterFactory :
660 "delimiter" - a one character delimiter. Default is | (pipe)
661 "encoder" - how to encode the following value into a playload
662 float -> org.apache.lucene.analysis.payloads.FloatEncoder,
663 integer -> o.a.l.a.p.IntegerEncoder
664 identity -> o.a.l.a.p.IdentityEncoder
665 Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
667 <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
671 <!-- lowercases the entire field value, keeping it as a single token. -->
672 <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
674 <tokenizer class="solr.KeywordTokenizerFactory"/>
675 <filter class="solr.LowerCaseFilterFactory" />
680 Example of using PathHierarchyTokenizerFactory at index time, so
681 queries for paths match documents at that path, or in descendent paths
683 <fieldType name="descendent_path" class="solr.TextField">
684 <analyzer type="index">
685 <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
687 <analyzer type="query">
688 <tokenizer class="solr.KeywordTokenizerFactory" />
692 Example of using PathHierarchyTokenizerFactory at query time, so
693 queries for paths match documents at that path, or in ancestor paths
695 <fieldType name="ancestor_path" class="solr.TextField">
696 <analyzer type="index">
697 <tokenizer class="solr.KeywordTokenizerFactory" />
699 <analyzer type="query">
700 <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
704 <!-- since fields of this type are by default not stored or indexed,
705 any data added to them will be ignored outright. -->
706 <fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
708 <!-- This point type indexes the coordinates as separate fields (subFields)
709 If subFieldType is defined, it references a type, and a dynamic field
710 definition is created matching *___<typename>. Alternately, if
711 subFieldSuffix is defined, that is used to create the subFields.
712 Example: if subFieldType="double", then the coordinates would be
713 indexed in fields myloc_0___double,myloc_1___double.
714 Example: if subFieldSuffix="_d" then the coordinates would be indexed
715 in fields myloc_0_d,myloc_1_d
716 The subFields are an implementation detail of the fieldType, and end
717 users normally should not need to know about them.
719 <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
721 <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
722 <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
725 A Geohash is a compact representation of a latitude longitude pair in a single field.
726 See http://wiki.apache.org/solr/SpatialSearch
728 <fieldtype name="geohash" class="solr.GeoHashField"/>
730 <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
732 defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
733 precisionStep: Specifies the precisionStep for the TrieLong field used for the amount
734 providerClass: Lets you plug in other exchange provider backend:
735 solr.FileExchangeRateProvider is the default and takes one parameter:
736 currencyConfig: name of an xml file holding exhange rates
737 solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
738 ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
739 refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
741 <!-- <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" /> - nie dziala -->
745 <!-- some examples for different languages (generally ordered by ISO code) -->
748 <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
750 <tokenizer class="solr.StandardTokenizerFactory"/>
751 <!-- for any non-arabic -->
752 <filter class="solr.LowerCaseFilterFactory"/>
753 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" enablePositionIncrements="true"/>
754 <!-- normalizes ﻯ to ﻱ, etc -->
755 <filter class="solr.ArabicNormalizationFilterFactory"/>
756 <filter class="solr.ArabicStemFilterFactory"/>
761 <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
763 <tokenizer class="solr.StandardTokenizerFactory"/>
764 <filter class="solr.LowerCaseFilterFactory"/>
765 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" enablePositionIncrements="true"/>
766 <filter class="solr.BulgarianStemFilterFactory"/>
771 <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
773 <tokenizer class="solr.StandardTokenizerFactory"/>
774 <!-- removes l', etc -->
775 <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
776 <filter class="solr.LowerCaseFilterFactory"/>
777 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" enablePositionIncrements="true"/>
778 <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
782 <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
783 <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
785 <tokenizer class="solr.StandardTokenizerFactory"/>
786 <!-- normalize width before bigram, as e.g. half-width dakuten combine -->
787 <filter class="solr.CJKWidthFilterFactory"/>
788 <!-- for any non-CJK -->
789 <filter class="solr.LowerCaseFilterFactory"/>
790 <filter class="solr.CJKBigramFilterFactory"/>
795 <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
797 <tokenizer class="solr.StandardTokenizerFactory"/>
798 <filter class="solr.LowerCaseFilterFactory"/>
799 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" enablePositionIncrements="true"/>
800 <filter class="solr.CzechStemFilterFactory"/>
805 <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
807 <tokenizer class="solr.StandardTokenizerFactory"/>
808 <filter class="solr.LowerCaseFilterFactory"/>
809 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" enablePositionIncrements="true"/>
810 <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
815 <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
817 <tokenizer class="solr.StandardTokenizerFactory"/>
818 <filter class="solr.LowerCaseFilterFactory"/>
819 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" enablePositionIncrements="true"/>
820 <filter class="solr.GermanNormalizationFilterFactory"/>
821 <filter class="solr.GermanLightStemFilterFactory"/>
822 <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
823 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
828 <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
830 <tokenizer class="solr.StandardTokenizerFactory"/>
831 <!-- greek specific lowercase for sigma -->
832 <filter class="solr.GreekLowerCaseFilterFactory"/>
833 <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" enablePositionIncrements="true"/>
834 <filter class="solr.GreekStemFilterFactory"/>
839 <fieldType name="text_es" 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_es.txt" format="snowball" enablePositionIncrements="true"/>
844 <filter class="solr.SpanishLightStemFilterFactory"/>
845 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
850 <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
852 <tokenizer class="solr.StandardTokenizerFactory"/>
853 <filter class="solr.LowerCaseFilterFactory"/>
854 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" enablePositionIncrements="true"/>
855 <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
860 <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
863 <charFilter class="solr.PersianCharFilterFactory"/>
864 <tokenizer class="solr.StandardTokenizerFactory"/>
865 <filter class="solr.LowerCaseFilterFactory"/>
866 <filter class="solr.ArabicNormalizationFilterFactory"/>
867 <filter class="solr.PersianNormalizationFilterFactory"/>
868 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" enablePositionIncrements="true"/>
873 <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
875 <tokenizer class="solr.StandardTokenizerFactory"/>
876 <filter class="solr.LowerCaseFilterFactory"/>
877 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" enablePositionIncrements="true"/>
878 <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
879 <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
884 <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
886 <tokenizer class="solr.StandardTokenizerFactory"/>
887 <!-- removes l', etc -->
888 <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
889 <filter class="solr.LowerCaseFilterFactory"/>
890 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" enablePositionIncrements="true"/>
891 <filter class="solr.FrenchLightStemFilterFactory"/>
892 <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
893 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
898 <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
900 <tokenizer class="solr.StandardTokenizerFactory"/>
901 <!-- removes d', etc -->
902 <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
903 <!-- removes n-, etc. position increments is intentionally false! -->
904 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt" enablePositionIncrements="false"/>
905 <filter class="solr.IrishLowerCaseFilterFactory"/>
906 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt" enablePositionIncrements="true"/>
907 <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
912 <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
914 <tokenizer class="solr.StandardTokenizerFactory"/>
915 <filter class="solr.LowerCaseFilterFactory"/>
916 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" enablePositionIncrements="true"/>
917 <filter class="solr.GalicianStemFilterFactory"/>
918 <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
923 <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
925 <tokenizer class="solr.StandardTokenizerFactory"/>
926 <filter class="solr.LowerCaseFilterFactory"/>
927 <!-- normalizes unicode representation -->
928 <filter class="solr.IndicNormalizationFilterFactory"/>
929 <!-- normalizes variation in spelling -->
930 <filter class="solr.HindiNormalizationFilterFactory"/>
931 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" enablePositionIncrements="true"/>
932 <filter class="solr.HindiStemFilterFactory"/>
937 <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
939 <tokenizer class="solr.StandardTokenizerFactory"/>
940 <filter class="solr.LowerCaseFilterFactory"/>
941 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" enablePositionIncrements="true"/>
942 <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
943 <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
948 <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
950 <tokenizer class="solr.StandardTokenizerFactory"/>
951 <filter class="solr.LowerCaseFilterFactory"/>
952 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" enablePositionIncrements="true"/>
953 <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
958 <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
960 <tokenizer class="solr.StandardTokenizerFactory"/>
961 <filter class="solr.LowerCaseFilterFactory"/>
962 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" enablePositionIncrements="true"/>
963 <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
964 <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
969 <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
971 <tokenizer class="solr.StandardTokenizerFactory"/>
972 <!-- removes l', etc -->
973 <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
974 <filter class="solr.LowerCaseFilterFactory"/>
975 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" enablePositionIncrements="true"/>
976 <filter class="solr.ItalianLightStemFilterFactory"/>
977 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
981 <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
983 NOTE: If you want to optimize search for precision, use default operator AND in your query
984 parser config with <solrQueryParser defaultOperator="AND"/> further down in this file. Use
985 OR if you would like to optimize for recall (default).
987 <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
989 <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
991 Kuromoji has a search mode (default) that does segmentation useful for search. A heuristic
992 is used to segment compounds into its parts and the compound itself is kept as synonym.
994 Valid values for attribute mode are:
995 normal: regular segmentation
996 search: segmentation useful for search with synonyms compounds (default)
997 extended: same as search mode, but unigrams unknown words (experimental)
999 For some applications it might be good to use search mode for indexing and normal mode for
1000 queries to reduce recall and prevent parts of compounds from being matched and highlighted.
1001 Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
1003 Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
1004 model with your own entries for segmentation, part-of-speech tags and readings without a need
1005 to specify weights. Notice that user dictionaries have not been subject to extensive testing.
1007 User dictionary attributes are:
1008 userDictionary: user dictionary filename
1009 userDictionaryEncoding: user dictionary encoding (default is UTF-8)
1011 See lang/userdict_ja.txt for a sample user dictionary file.
1013 Punctuation characters are discarded by default. Use discardPunctuation="false" to keep them.
1015 See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
1017 <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
1018 <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
1019 <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
1020 <filter class="solr.JapaneseBaseFormFilterFactory"/>
1021 <!-- Removes tokens with certain part-of-speech tags -->
1022 <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" enablePositionIncrements="true"/>
1023 <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
1024 <filter class="solr.CJKWidthFilterFactory"/>
1025 <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
1026 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" enablePositionIncrements="true" />
1027 <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
1028 <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
1029 <!-- Lower-cases romaji characters -->
1030 <filter class="solr.LowerCaseFilterFactory"/>
1035 <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
1037 <tokenizer class="solr.StandardTokenizerFactory"/>
1038 <filter class="solr.LowerCaseFilterFactory"/>
1039 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" enablePositionIncrements="true"/>
1040 <filter class="solr.LatvianStemFilterFactory"/>
1045 <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
1047 <tokenizer class="solr.StandardTokenizerFactory"/>
1048 <filter class="solr.LowerCaseFilterFactory"/>
1049 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" enablePositionIncrements="true"/>
1050 <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
1051 <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
1056 <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
1058 <tokenizer class="solr.StandardTokenizerFactory"/>
1059 <filter class="solr.LowerCaseFilterFactory"/>
1060 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" enablePositionIncrements="true"/>
1061 <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
1062 <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> -->
1063 <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
1068 <fieldType name="text_pl" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
1070 <tokenizer class="solr.StandardTokenizerFactory"/>
1071 <filter class="solr.LowerCaseFilterFactory"/>
1072 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pl.txt" format="snowball" enablePositionIncrements="true"/>
1073 <filter class="solr.MorfologikFilterFactory" dictionary="MORFOLOGIK" />
1074 <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
1075 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
1076 <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
1080 <fieldType name="text_pl_nonstop" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
1082 <tokenizer class="solr.StandardTokenizerFactory"/>
1083 <filter class="solr.LowerCaseFilterFactory"/>
1084 <filter class="solr.MorfologikFilterFactory" dictionary="MORFOLOGIK" />
1085 <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
1086 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
1087 <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
1092 <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
1094 <tokenizer class="solr.StandardTokenizerFactory"/>
1095 <filter class="solr.LowerCaseFilterFactory"/>
1096 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" enablePositionIncrements="true"/>
1097 <filter class="solr.PortugueseLightStemFilterFactory"/>
1098 <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
1099 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
1100 <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
1105 <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
1107 <tokenizer class="solr.StandardTokenizerFactory"/>
1108 <filter class="solr.LowerCaseFilterFactory"/>
1109 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" enablePositionIncrements="true"/>
1110 <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
1115 <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
1117 <tokenizer class="solr.StandardTokenizerFactory"/>
1118 <filter class="solr.LowerCaseFilterFactory"/>
1119 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" enablePositionIncrements="true"/>
1120 <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
1121 <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
1126 <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
1128 <tokenizer class="solr.StandardTokenizerFactory"/>
1129 <filter class="solr.LowerCaseFilterFactory"/>
1130 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" enablePositionIncrements="true"/>
1131 <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
1132 <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
1137 <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
1139 <tokenizer class="solr.StandardTokenizerFactory"/>
1140 <filter class="solr.LowerCaseFilterFactory"/>
1141 <filter class="solr.ThaiWordFilterFactory"/>
1142 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" enablePositionIncrements="true"/>
1147 <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
1149 <tokenizer class="solr.StandardTokenizerFactory"/>
1150 <filter class="solr.TurkishLowerCaseFilterFactory"/>
1151 <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" enablePositionIncrements="true"/>
1152 <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
1158 <!-- Similarity is the scoring routine for each document vs. a query.
1159 A custom Similarity or SimilarityFactory may be specified here, but
1160 the default is fine for most applications.
1161 For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
1164 <similarity class="com.example.solr.CustomSimilarityFactory">
1165 <str name="paramkey">param value</str>