source: gs3-extensions/solr/trunk/src/conf/schema.xml@ 29985

Last change on this file since 29985 was 29985, checked in by Georgiy Litvinov, 7 years ago

Added russian morphology analyzer description to schema.xml

File size: 58.9 KB
Line 
1<?xml version="1.0" encoding="UTF-8" ?>
2<!--
3 Licensed to the Apache Software Foundation (ASF) under one or more
4 contributor license agreements. See the NOTICE file distributed with
5 this work for additional information regarding copyright ownership.
6 The ASF licenses this file to You under the Apache License, Version 2.0
7 (the "License"); you may not use this file except in compliance with
8 the License. You may obtain a copy of the License at
9
10 http://www.apache.org/licenses/LICENSE-2.0
11
12 Unless required by applicable law or agreed to in writing, software
13 distributed under the License is distributed on an "AS IS" BASIS,
14 WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15 See the License for the specific language governing permissions and
16 limitations under the License.
17-->
18
19<!--
20 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.
24
25 This example schema is the recommended starting point for users.
26 It should be kept correct and concise, usable out-of-the-box.
27
28 For more information, on how to customize this file, please see
29 http://wiki.apache.org/solr/SchemaXml
30
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
35 value.
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
43 java client.
44 - Remember to run the JVM in server mode, and use a higher logging level
45 that avoids logging every request
46-->
47
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
51 semantics. It should not normally be changed by applications.
52
53 1.0: multiValued attribute did not exist, all fields are multiValued
54 by nature
55 1.1: multiValued attribute introduced, false by default
56 1.2: omitTermFreqAndPositions attribute introduced, true by default
57 except for text fields.
58 1.3: removed optional field compress feature
59 1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser
60 behavior when a single string produces multiple tokens. Defaults
61 to off for version >= 1.4
62 1.5: omitNorms defaults to true for primitive field types
63 (int, float, boolean, string...)
64 -->
65
66<fields>
67 <!-- Valid attributes for fields:
68 name: mandatory - the name for the field
69 type: mandatory - the name of a field type from the
70 <types> fieldType section
71 indexed: true if this field should be indexed (searchable or sortable)
72 stored: true if this field should be retrievable
73 docValues: true if this field should have doc values. Doc values are
74 useful for faceting, grouping, sorting and function queries. Although not
75 required, doc values will make the index faster to load, more
76 NRT-friendly and more memory-efficient. They however come with some
77 limitations: they are currently only supported by StrField, UUIDField
78 and all Trie*Fields, and depending on the field type, they might
79 require the field to be single-valued, be required or have a default
80 value (check the documentation of the field type you're interested in
81 for more information)
82 multiValued: true if this field may contain multiple values per document
83 omitNorms: (expert) set to true to omit the norms associated with
84 this field (this disables length normalization and index-time
85 boosting for the field, and saves some memory). Only full-text
86 fields or fields that need an index-time boost need norms.
87 Norms are omitted for primitive (non-analyzed) types by default.
88 termVectors: [false] set to true to store the term vector for a
89 given field.
90 When using MoreLikeThis, fields used for similarity should be
91 stored for best performance.
92 termPositions: Store position information with the term vector.
93 This will increase storage costs.
94 termOffsets: Store offset information with the term vector. This
95 will increase storage costs.
96 required: The field is required. It will throw an error if the
97 value does not exist
98 default: a value that should be used if no value is specified
99 when adding a document.
100 -->
101
102 <!-- field names should consist of alphanumeric or underscore characters only and
103 not start with a digit. This is not currently strictly enforced,
104 but other field names will not have first class support from all components
105 and back compatibility is not guaranteed. Names with both leading and
106 trailing underscores (e.g. _version_) are reserved.
107 -->
108
109 <!-- If you remove this field, you must _also_ disable the update log in solrconfig.xml
110 or Solr won't start. _version_ and update log are required for SolrCloud
111 -->
112 <field name="_version_" type="long" indexed="true" stored="true"/>
113
114 <!-- points to the root document of a block of nested documents. Required for nested
115 document support, may be removed otherwise
116 -->
117 <field name="_root_" type="string" indexed="true" stored="false"/>
118
119 <!-- Only remove the "id" field if you have a very good reason to. While not strictly
120 required, it is highly recommended. A <uniqueKey> is present in almost all Solr
121 installations. See the <uniqueKey> declaration below where <uniqueKey> is set to "id".
122 -->
123 <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
124
125 <field name="sku" type="text_en_splitting_tight" indexed="true" stored="true" omitNorms="true"/>
126 <field name="name" type="text_general" indexed="true" stored="true"/>
127 <field name="manu" type="text_general" indexed="true" stored="true" omitNorms="true"/>
128 <field name="cat" type="string" indexed="true" stored="true" multiValued="true"/>
129 <field name="features" type="text_general" indexed="true" stored="true" multiValued="true"/>
130 <field name="includes" type="text_general" indexed="true" stored="true" termVectors="true" termPositions="true" termOffsets="true" />
131
132 <field name="weight" type="float" indexed="true" stored="true"/>
133 <field name="price" type="float" indexed="true" stored="true"/>
134 <field name="popularity" type="int" indexed="true" stored="true" />
135 <field name="inStock" type="boolean" indexed="true" stored="true" />
136
137 <field name="store" type="location" indexed="true" stored="true"/>
138
139 <!-- Common metadata fields, named specifically to match up with
140 SolrCell metadata when parsing rich documents such as Word, PDF.
141 Some fields are multiValued only because Tika currently may return
142 multiple values for them. Some metadata is parsed from the documents,
143 but there are some which come from the client context:
144 "content_type": From the HTTP headers of incoming stream
145 "resourcename": From SolrCell request param resource.name
146 -->
147 <field name="title" type="text_general" indexed="true" stored="true" multiValued="true"/>
148 <field name="subject" type="text_general" indexed="true" stored="true"/>
149 <field name="description" type="text_general" indexed="true" stored="true"/>
150 <field name="comments" type="text_general" indexed="true" stored="true"/>
151 <field name="author" type="text_general" indexed="true" stored="true"/>
152 <field name="keywords" type="text_general" indexed="true" stored="true"/>
153 <field name="category" type="text_general" indexed="true" stored="true"/>
154 <field name="resourcename" type="text_general" indexed="true" stored="true"/>
155 <field name="url" type="text_general" indexed="true" stored="true"/>
156 <field name="content_type" type="string" indexed="true" stored="true" multiValued="true"/>
157 <field name="last_modified" type="date" indexed="true" stored="true"/>
158 <field name="links" type="string" indexed="true" stored="true" multiValued="true"/>
159
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"/>
165
166
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"/>
170
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"/>
174
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"/>
178
179 <field name="payloads" type="payloads" indexed="true" stored="true"/>
180
181
182 <!--
183 Some fields such as popularity and manu_exact could be modified to
184 leverage doc values:
185 <field name="popularity" type="int" indexed="true" stored="true" docValues="true" />
186 <field name="manu_exact" type="string" indexed="false" stored="false" docValues="true" />
187 <field name="cat" type="string" indexed="true" stored="true" docValues="true" multiValued="true"/>
188
189
190 Although it would make indexing slightly slower and the index bigger, it
191 would also make the index faster to load, more memory-efficient and more
192 NRT-friendly.
193 -->
194
195 <!-- Dynamic field definitions allow using convention over configuration
196 for fields via the specification of patterns to match field names.
197 EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
198 RESTRICTION: the glob-like pattern in the name attribute must have
199 a "*" only at the start or the end. -->
200
201 <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
202 <dynamicField name="*_is" type="int" indexed="true" stored="true" multiValued="true"/>
203 <dynamicField name="*_s" type="string" indexed="true" stored="true" />
204 <dynamicField name="*_ss" type="string" indexed="true" stored="true" multiValued="true"/>
205 <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
206 <dynamicField name="*_ls" type="long" indexed="true" stored="true" multiValued="true"/>
207 <dynamicField name="*_t" type="text_general" indexed="true" stored="true"/>
208 <dynamicField name="*_txt" type="text_general" indexed="true" stored="true" multiValued="true"/>
209 <dynamicField name="*_en" type="text_en" indexed="true" stored="true" multiValued="true"/>
210 <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
211 <dynamicField name="*_bs" type="boolean" indexed="true" stored="true" multiValued="true"/>
212 <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
213 <dynamicField name="*_fs" type="float" indexed="true" stored="true" multiValued="true"/>
214 <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
215 <dynamicField name="*_ds" type="double" indexed="true" stored="true" multiValued="true"/>
216
217 <!-- Type used to index the lat and lon components for the "location" FieldType -->
218 <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false" />
219
220 <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
221 <dynamicField name="*_dts" type="date" indexed="true" stored="true" multiValued="true"/>
222 <dynamicField name="*_p" type="location" indexed="true" stored="true"/>
223
224 <!-- some trie-coded dynamic fields for faster range queries -->
225 <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
226 <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
227 <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
228 <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
229 <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
230
231 <dynamicField name="*_pi" type="pint" indexed="true" stored="true"/>
232 <dynamicField name="*_c" type="currency" indexed="true" stored="true"/>
233
234 <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
235 <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
236
237 <dynamicField name="random_*" type="random" />
238
239 <!-- uncomment the following to ignore any fields that don't already match an existing
240 field name or dynamic field, rather than reporting them as an error.
241 alternately, change the type="ignored" to some other type e.g. "text" if you want
242 unknown fields indexed and/or stored by default -->
243 <!--dynamicField name="*" type="ignored" multiValued="true" /-->
244
245 </fields>
246
247
248 <!-- Field to use to determine and enforce document uniqueness.
249 Unless this field is marked with required="false", it will be a required field
250 -->
251 <uniqueKey>id</uniqueKey>
252
253 <!-- DEPRECATED: The defaultSearchField is consulted by various query parsers when
254 parsing a query string that isn't explicit about the field. Machine (non-user)
255 generated queries are best made explicit, or they can use the "df" request parameter
256 which takes precedence over this.
257 Note: Un-commenting defaultSearchField will be insufficient if your request handler
258 in solrconfig.xml defines "df", which takes precedence. That would need to be removed.
259 <defaultSearchField>text</defaultSearchField> -->
260
261 <!-- DEPRECATED: The defaultOperator (AND|OR) is consulted by various query parsers
262 when parsing a query string to determine if a clause of the query should be marked as
263 required or optional, assuming the clause isn't already marked by some operator.
264 The default is OR, which is generally assumed so it is not a good idea to change it
265 globally here. The "q.op" request parameter takes precedence over this.
266 <solrQueryParser defaultOperator="OR"/> -->
267
268 <!-- copyField commands copy one field to another at the time a document
269 is added to the index. It's used either to index the same field differently,
270 or to add multiple fields to the same field for easier/faster searching. -->
271
272 <copyField source="cat" dest="text"/>
273 <copyField source="name" dest="text"/>
274 <copyField source="manu" dest="text"/>
275 <copyField source="features" dest="text"/>
276 <copyField source="includes" dest="text"/>
277 <copyField source="manu" dest="manu_exact"/>
278
279 <!-- Copy the price into a currency enabled field (default USD) -->
280 <copyField source="price" dest="price_c"/>
281
282 <!-- Text fields from SolrCell to search by default in our catch-all field -->
283 <copyField source="title" dest="text"/>
284 <copyField source="author" dest="text"/>
285 <copyField source="description" dest="text"/>
286 <copyField source="keywords" dest="text"/>
287 <copyField source="content" dest="text"/>
288 <copyField source="content_type" dest="text"/>
289 <copyField source="resourcename" dest="text"/>
290 <copyField source="url" dest="text"/>
291
292 <!-- Create a string version of author for faceting -->
293 <copyField source="author" dest="author_s"/>
294
295 <!-- Above, multiple source fields are copied to the [text] field.
296 Another way to map multiple source fields to the same
297 destination field is to use the dynamic field syntax.
298 copyField also supports a maxChars to copy setting. -->
299
300 <!-- <copyField source="*_t" dest="text" maxChars="3000"/> -->
301
302 <!-- copy name to alphaNameSort, a field designed for sorting by name -->
303 <!-- <copyField source="name" dest="alphaNameSort"/> -->
304
305 <types>
306 <!-- field type definitions. The "name" attribute is
307 just a label to be used by field definitions. The "class"
308 attribute and any other attributes determine the real
309 behavior of the fieldType.
310 Class names starting with "solr" refer to java classes in a
311 standard package such as org.apache.solr.analysis
312 -->
313
314 <!-- The StrField type is not analyzed, but indexed/stored verbatim.
315 It supports doc values but in that case the field needs to be
316 single-valued and either required or have a default value.
317 -->
318 <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
319
320 <!-- boolean type: "true" or "false" -->
321 <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
322
323 <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
324 currently supported on types that are sorted internally as strings
325 and on numeric types.
326 This includes "string","boolean", and, as of 3.5 (and 4.x),
327 int, float, long, date, double, including the "Trie" variants.
328 - If sortMissingLast="true", then a sort on this field will cause documents
329 without the field to come after documents with the field,
330 regardless of the requested sort order (asc or desc).
331 - If sortMissingFirst="true", then a sort on this field will cause documents
332 without the field to come before documents with the field,
333 regardless of the requested sort order.
334 - If sortMissingLast="false" and sortMissingFirst="false" (the default),
335 then default lucene sorting will be used which places docs without the
336 field first in an ascending sort and last in a descending sort.
337 -->
338
339 <!--
340 Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
341
342 These fields support doc values, but they require the field to be
343 single-valued and either be required or have a default value.
344 -->
345 <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
346 <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
347 <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
348 <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
349
350 <!--
351 Numeric field types that index each value at various levels of precision
352 to accelerate range queries when the number of values between the range
353 endpoints is large. See the javadoc for NumericRangeQuery for internal
354 implementation details.
355
356 Smaller precisionStep values (specified in bits) will lead to more tokens
357 indexed per value, slightly larger index size, and faster range queries.
358 A precisionStep of 0 disables indexing at different precision levels.
359 -->
360 <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
361 <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
362 <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
363 <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
364
365 <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
366 is a more restricted form of the canonical representation of dateTime
367 http://www.w3.org/TR/xmlschema-2/#dateTime
368 The trailing "Z" designates UTC time and is mandatory.
369 Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
370 All other components are mandatory.
371
372 Expressions can also be used to denote calculations that should be
373 performed relative to "NOW" to determine the value, ie...
374
375 NOW/HOUR
376 ... Round to the start of the current hour
377 NOW-1DAY
378 ... Exactly 1 day prior to now
379 NOW/DAY+6MONTHS+3DAYS
380 ... 6 months and 3 days in the future from the start of
381 the current day
382
383 Consult the DateField javadocs for more information.
384
385 Note: For faster range queries, consider the tdate type
386 -->
387 <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
388
389 <!-- A Trie based date field for faster date range queries and date faceting. -->
390 <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
391
392
393 <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
394 <fieldtype name="binary" class="solr.BinaryField"/>
395
396 <!--
397 Note:
398 These should only be used for compatibility with existing indexes (created with lucene or older Solr versions).
399 Use Trie based fields instead. As of Solr 3.5 and 4.x, Trie based fields support sortMissingFirst/Last
400
401 Plain numeric field types that store and index the text
402 value verbatim (and hence don't correctly support range queries, since the
403 lexicographic ordering isn't equal to the numeric ordering)
404 -->
405 <fieldType name="pint" class="solr.IntField"/>
406 <fieldType name="plong" class="solr.LongField"/>
407 <fieldType name="pfloat" class="solr.FloatField"/>
408 <fieldType name="pdouble" class="solr.DoubleField"/>
409 <fieldType name="pdate" class="solr.DateField" sortMissingLast="true"/>
410
411 <!-- The "RandomSortField" is not used to store or search any
412 data. You can declare fields of this type it in your schema
413 to generate pseudo-random orderings of your docs for sorting
414 or function purposes. The ordering is generated based on the field
415 name and the version of the index. As long as the index version
416 remains unchanged, and the same field name is reused,
417 the ordering of the docs will be consistent.
418 If you want different psuedo-random orderings of documents,
419 for the same version of the index, use a dynamicField and
420 change the field name in the request.
421 -->
422 <fieldType name="random" class="solr.RandomSortField" indexed="true" />
423
424 <!-- solr.TextField allows the specification of custom text analyzers
425 specified as a tokenizer and a list of token filters. Different
426 analyzers may be specified for indexing and querying.
427
428 The optional positionIncrementGap puts space between multiple fields of
429 this type on the same document, with the purpose of preventing false phrase
430 matching across fields.
431
432 For more info on customizing your analyzer chain, please see
433 http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
434 -->
435
436 <!-- One can also specify an existing Analyzer class that has a
437 default constructor via the class attribute on the analyzer element.
438 Example:
439 <fieldType name="text_greek" class="solr.TextField">
440 <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
441 </fieldType>
442 -->
443
444 <!-- A text field that only splits on whitespace for exact matching of words -->
445 <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
446 <analyzer>
447 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
448 </analyzer>
449 </fieldType>
450
451 <!-- A general text field that has reasonable, generic
452 cross-language defaults: it tokenizes with StandardTokenizer,
453 removes stop words from case-insensitive "stopwords.txt"
454 (empty by default), and down cases. At query time only, it
455 also applies synonyms. -->
456 <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
457 <analyzer type="index">
458 <tokenizer class="solr.StandardTokenizerFactory"/>
459 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
460 <!-- in this example, we will only use synonyms at query time
461 <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
462 -->
463 <filter class="solr.LowerCaseFilterFactory"/>
464 </analyzer>
465 <analyzer type="query">
466 <tokenizer class="solr.StandardTokenizerFactory"/>
467 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
468 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
469 <filter class="solr.LowerCaseFilterFactory"/>
470 </analyzer>
471 </fieldType>
472
473 <!-- A text field with defaults appropriate for English: it
474 tokenizes with StandardTokenizer, removes English stop words
475 (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
476 finally applies Porter's stemming. The query time analyzer
477 also applies synonyms from synonyms.txt. -->
478 <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
479 <analyzer type="index">
480 <tokenizer class="solr.StandardTokenizerFactory"/>
481 <!-- in this example, we will only use synonyms at query time
482 <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
483 -->
484 <!-- Case insensitive stop word removal.
485 -->
486 <filter class="solr.StopFilterFactory"
487 ignoreCase="true"
488 words="lang/stopwords_en.txt"
489 />
490 <filter class="solr.LowerCaseFilterFactory"/>
491 <filter class="solr.EnglishPossessiveFilterFactory"/>
492 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
493 <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
494 <filter class="solr.EnglishMinimalStemFilterFactory"/>
495 -->
496 <filter class="solr.PorterStemFilterFactory"/>
497 </analyzer>
498 <analyzer type="query">
499 <tokenizer class="solr.StandardTokenizerFactory"/>
500 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
501 <filter class="solr.StopFilterFactory"
502 ignoreCase="true"
503 words="lang/stopwords_en.txt"
504 />
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"/>
510 -->
511 <filter class="solr.PorterStemFilterFactory"/>
512 </analyzer>
513 </fieldType>
514
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".
523 -->
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"/>
529 -->
530 <!-- Case insensitive stop word removal.
531 -->
532 <filter class="solr.StopFilterFactory"
533 ignoreCase="true"
534 words="lang/stopwords_en.txt"
535 />
536 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
537 <filter class="solr.LowerCaseFilterFactory"/>
538 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
539 <filter class="solr.PorterStemFilterFactory"/>
540 </analyzer>
541 <analyzer type="query">
542 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
543 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
544 <filter class="solr.StopFilterFactory"
545 ignoreCase="true"
546 words="lang/stopwords_en.txt"
547 />
548 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
549 <filter class="solr.LowerCaseFilterFactory"/>
550 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
551 <filter class="solr.PorterStemFilterFactory"/>
552 </analyzer>
553 </fieldType>
554
555 <!-- Less flexible matching, but less false matches. Probably not ideal for product names,
556 but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
557 <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
558 <analyzer>
559 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
560 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
561 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
562 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
563 <filter class="solr.LowerCaseFilterFactory"/>
564 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
565 <filter class="solr.EnglishMinimalStemFilterFactory"/>
566 <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
567 possible with WordDelimiterFilter in conjuncton with stemming. -->
568 <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
569 </analyzer>
570 </fieldType>
571
572 <!-- Just like text_general except it reverses the characters of
573 each token, to enable more efficient leading wildcard queries. -->
574 <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
575 <analyzer type="index">
576 <tokenizer class="solr.StandardTokenizerFactory"/>
577 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
578 <filter class="solr.LowerCaseFilterFactory"/>
579 <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
580 maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
581 </analyzer>
582 <analyzer type="query">
583 <tokenizer class="solr.StandardTokenizerFactory"/>
584 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
585 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
586 <filter class="solr.LowerCaseFilterFactory"/>
587 </analyzer>
588 </fieldType>
589
590 <!-- charFilter + WhitespaceTokenizer -->
591 <!--
592 <fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
593 <analyzer>
594 <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
595 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
596 </analyzer>
597 </fieldType>
598 -->
599
600 <!-- This is an example of using the KeywordTokenizer along
601 With various TokenFilterFactories to produce a sortable field
602 that does not include some properties of the source text
603 -->
604 <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
605 <analyzer>
606 <!-- KeywordTokenizer does no actual tokenizing, so the entire
607 input string is preserved as a single token
608 -->
609 <tokenizer class="solr.KeywordTokenizerFactory"/>
610 <!-- The LowerCase TokenFilter does what you expect, which can be
611 when you want your sorting to be case insensitive
612 -->
613 <filter class="solr.LowerCaseFilterFactory" />
614 <!-- The TrimFilter removes any leading or trailing whitespace -->
615 <filter class="solr.TrimFilterFactory" />
616 <!-- The PatternReplaceFilter gives you the flexibility to use
617 Java Regular expression to replace any sequence of characters
618 matching a pattern with an arbitrary replacement string,
619 which may include back references to portions of the original
620 string matched by the pattern.
621
622 See the Java Regular Expression documentation for more
623 information on pattern and replacement string syntax.
624
625 http://java.sun.com/j2se/1.6.0/docs/api/java/util/regex/package-summary.html
626 -->
627 <filter class="solr.PatternReplaceFilterFactory"
628 pattern="([^a-z])" replacement="" replace="all"
629 />
630 </analyzer>
631 </fieldType>
632
633 <fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
634 <analyzer>
635 <tokenizer class="solr.StandardTokenizerFactory"/>
636 <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
637 </analyzer>
638 </fieldtype>
639
640 <fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
641 <analyzer>
642 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
643 <!--
644 The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
645 a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
646 Attributes of the DelimitedPayloadTokenFilterFactory :
647 "delimiter" - a one character delimiter. Default is | (pipe)
648 "encoder" - how to encode the following value into a playload
649 float -> org.apache.lucene.analysis.payloads.FloatEncoder,
650 integer -> o.a.l.a.p.IntegerEncoder
651 identity -> o.a.l.a.p.IdentityEncoder
652 Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
653 -->
654 <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
655 </analyzer>
656 </fieldtype>
657
658 <!-- lowercases the entire field value, keeping it as a single token. -->
659 <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
660 <analyzer>
661 <tokenizer class="solr.KeywordTokenizerFactory"/>
662 <filter class="solr.LowerCaseFilterFactory" />
663 </analyzer>
664 </fieldType>
665
666 <!--
667 Example of using PathHierarchyTokenizerFactory at index time, so
668 queries for paths match documents at that path, or in descendent paths
669 -->
670 <fieldType name="descendent_path" class="solr.TextField">
671 <analyzer type="index">
672 <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
673 </analyzer>
674 <analyzer type="query">
675 <tokenizer class="solr.KeywordTokenizerFactory" />
676 </analyzer>
677 </fieldType>
678 <!--
679 Example of using PathHierarchyTokenizerFactory at query time, so
680 queries for paths match documents at that path, or in ancestor paths
681 -->
682 <fieldType name="ancestor_path" class="solr.TextField">
683 <analyzer type="index">
684 <tokenizer class="solr.KeywordTokenizerFactory" />
685 </analyzer>
686 <analyzer type="query">
687 <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
688 </analyzer>
689 </fieldType>
690
691 <!-- since fields of this type are by default not stored or indexed,
692 any data added to them will be ignored outright. -->
693 <fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
694
695 <!-- This point type indexes the coordinates as separate fields (subFields)
696 If subFieldType is defined, it references a type, and a dynamic field
697 definition is created matching *___<typename>. Alternately, if
698 subFieldSuffix is defined, that is used to create the subFields.
699 Example: if subFieldType="double", then the coordinates would be
700 indexed in fields myloc_0___double,myloc_1___double.
701 Example: if subFieldSuffix="_d" then the coordinates would be indexed
702 in fields myloc_0_d,myloc_1_d
703 The subFields are an implementation detail of the fieldType, and end
704 users normally should not need to know about them.
705 -->
706 <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
707
708 <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
709 <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
710
711 <!-- An alternative geospatial field type new to Solr 4. It supports multiValued and polygon shapes.
712 For more information about this and other Spatial fields new to Solr 4, see:
713 http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
714 -->
715 <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
716 geo="true" distErrPct="0.025" maxDistErr="0.000009" units="degrees" />
717
718 <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
719 Parameters:
720 defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
721 precisionStep: Specifies the precisionStep for the TrieLong field used for the amount
722 providerClass: Lets you plug in other exchange provider backend:
723 solr.FileExchangeRateProvider is the default and takes one parameter:
724 currencyConfig: name of an xml file holding exchange rates
725 solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
726 ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
727 refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
728 -->
729 <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
730
731
732
733 <!-- some examples for different languages (generally ordered by ISO code) -->
734
735 <!-- Arabic -->
736 <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
737 <analyzer>
738 <tokenizer class="solr.StandardTokenizerFactory"/>
739 <!-- for any non-arabic -->
740 <filter class="solr.LowerCaseFilterFactory"/>
741 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
742 <!-- normalizes ﻯ to ﻱ, etc -->
743 <filter class="solr.ArabicNormalizationFilterFactory"/>
744 <filter class="solr.ArabicStemFilterFactory"/>
745 </analyzer>
746 </fieldType>
747
748 <!-- Bulgarian -->
749 <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
750 <analyzer>
751 <tokenizer class="solr.StandardTokenizerFactory"/>
752 <filter class="solr.LowerCaseFilterFactory"/>
753 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" />
754 <filter class="solr.BulgarianStemFilterFactory"/>
755 </analyzer>
756 </fieldType>
757
758 <!-- Catalan -->
759 <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
760 <analyzer>
761 <tokenizer class="solr.StandardTokenizerFactory"/>
762 <!-- removes l', etc -->
763 <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
764 <filter class="solr.LowerCaseFilterFactory"/>
765 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" />
766 <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
767 </analyzer>
768 </fieldType>
769
770 <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
771 <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
772 <analyzer>
773 <tokenizer class="solr.StandardTokenizerFactory"/>
774 <!-- normalize width before bigram, as e.g. half-width dakuten combine -->
775 <filter class="solr.CJKWidthFilterFactory"/>
776 <!-- for any non-CJK -->
777 <filter class="solr.LowerCaseFilterFactory"/>
778 <filter class="solr.CJKBigramFilterFactory"/>
779 </analyzer>
780 </fieldType>
781
782 <!-- Kurdish -->
783 <fieldType name="text_ckb" class="solr.TextField" positionIncrementGap="100">
784 <analyzer>
785 <tokenizer class="solr.StandardTokenizerFactory"/>
786 <filter class="solr.SoraniNormalizationFilterFactory"/>
787 <!-- for any latin text -->
788 <filter class="solr.LowerCaseFilterFactory"/>
789 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ckb.txt"/>
790 <filter class="solr.SoraniStemFilterFactory"/>
791 </analyzer>
792 </fieldType>
793
794 <!-- Czech -->
795 <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
796 <analyzer>
797 <tokenizer class="solr.StandardTokenizerFactory"/>
798 <filter class="solr.LowerCaseFilterFactory"/>
799 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" />
800 <filter class="solr.CzechStemFilterFactory"/>
801 </analyzer>
802 </fieldType>
803
804 <!-- Danish -->
805 <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
806 <analyzer>
807 <tokenizer class="solr.StandardTokenizerFactory"/>
808 <filter class="solr.LowerCaseFilterFactory"/>
809 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
810 <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
811 </analyzer>
812 </fieldType>
813
814 <!-- German -->
815 <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
816 <analyzer>
817 <tokenizer class="solr.StandardTokenizerFactory"/>
818 <filter class="solr.LowerCaseFilterFactory"/>
819 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" />
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"/> -->
824 </analyzer>
825 </fieldType>
826
827 <!-- Greek -->
828 <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
829 <analyzer>
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" />
834 <filter class="solr.GreekStemFilterFactory"/>
835 </analyzer>
836 </fieldType>
837
838 <!-- Spanish -->
839 <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
840 <analyzer>
841 <tokenizer class="solr.StandardTokenizerFactory"/>
842 <filter class="solr.LowerCaseFilterFactory"/>
843 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
844 <filter class="solr.SpanishLightStemFilterFactory"/>
845 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
846 </analyzer>
847 </fieldType>
848
849 <!-- Basque -->
850 <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
851 <analyzer>
852 <tokenizer class="solr.StandardTokenizerFactory"/>
853 <filter class="solr.LowerCaseFilterFactory"/>
854 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" />
855 <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
856 </analyzer>
857 </fieldType>
858
859 <!-- Persian -->
860 <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
861 <analyzer>
862 <!-- for ZWNJ -->
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" />
869 </analyzer>
870 </fieldType>
871
872 <!-- Finnish -->
873 <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
874 <analyzer>
875 <tokenizer class="solr.StandardTokenizerFactory"/>
876 <filter class="solr.LowerCaseFilterFactory"/>
877 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
878 <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
879 <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
880 </analyzer>
881 </fieldType>
882
883 <!-- French -->
884 <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
885 <analyzer>
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" />
891 <filter class="solr.FrenchLightStemFilterFactory"/>
892 <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
893 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
894 </analyzer>
895 </fieldType>
896
897 <!-- Irish -->
898 <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
899 <analyzer>
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"/>
905 <filter class="solr.IrishLowerCaseFilterFactory"/>
906 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/>
907 <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
908 </analyzer>
909 </fieldType>
910
911 <!-- Galician -->
912 <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
913 <analyzer>
914 <tokenizer class="solr.StandardTokenizerFactory"/>
915 <filter class="solr.LowerCaseFilterFactory"/>
916 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" />
917 <filter class="solr.GalicianStemFilterFactory"/>
918 <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
919 </analyzer>
920 </fieldType>
921
922 <!-- Hindi -->
923 <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
924 <analyzer>
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" />
932 <filter class="solr.HindiStemFilterFactory"/>
933 </analyzer>
934 </fieldType>
935
936 <!-- Hungarian -->
937 <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
938 <analyzer>
939 <tokenizer class="solr.StandardTokenizerFactory"/>
940 <filter class="solr.LowerCaseFilterFactory"/>
941 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
942 <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
943 <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
944 </analyzer>
945 </fieldType>
946
947 <!-- Armenian -->
948 <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
949 <analyzer>
950 <tokenizer class="solr.StandardTokenizerFactory"/>
951 <filter class="solr.LowerCaseFilterFactory"/>
952 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" />
953 <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
954 </analyzer>
955 </fieldType>
956
957 <!-- Indonesian -->
958 <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
959 <analyzer>
960 <tokenizer class="solr.StandardTokenizerFactory"/>
961 <filter class="solr.LowerCaseFilterFactory"/>
962 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" />
963 <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
964 <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
965 </analyzer>
966 </fieldType>
967
968 <!-- Italian -->
969 <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
970 <analyzer>
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" />
976 <filter class="solr.ItalianLightStemFilterFactory"/>
977 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
978 </analyzer>
979 </fieldType>
980
981 <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
982
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).
986 -->
987 <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
988 <analyzer>
989 <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
990
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.
993
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)
998
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.
1002
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.
1006
1007 User dictionary attributes are:
1008 userDictionary: user dictionary filename
1009 userDictionaryEncoding: user dictionary encoding (default is UTF-8)
1010
1011 See lang/userdict_ja.txt for a sample user dictionary file.
1012
1013 Punctuation characters are discarded by default. Use discardPunctuation="false" to keep them.
1014
1015 See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
1016 -->
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 (蟞曞圢) -->
1020 <filter class="solr.JapaneseBaseFormFilterFactory"/>
1021 <!-- Removes tokens with certain part-of-speech tags -->
1022 <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
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" />
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"/>
1031 </analyzer>
1032 </fieldType>
1033
1034 <!-- Latvian -->
1035 <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
1036 <analyzer>
1037 <tokenizer class="solr.StandardTokenizerFactory"/>
1038 <filter class="solr.LowerCaseFilterFactory"/>
1039 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" />
1040 <filter class="solr.LatvianStemFilterFactory"/>
1041 </analyzer>
1042 </fieldType>
1043
1044 <!-- Dutch -->
1045 <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
1046 <analyzer>
1047 <tokenizer class="solr.StandardTokenizerFactory"/>
1048 <filter class="solr.LowerCaseFilterFactory"/>
1049 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
1050 <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
1051 <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
1052 </analyzer>
1053 </fieldType>
1054
1055 <!-- Norwegian -->
1056 <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
1057 <analyzer>
1058 <tokenizer class="solr.StandardTokenizerFactory"/>
1059 <filter class="solr.LowerCaseFilterFactory"/>
1060 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
1061 <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
1062 <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory" variant="nb"/> -->
1063 <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory" variant="nb"/> -->
1064 <!-- The "light" and "minimal" stemmers support variants: nb=Bokmål, nn=Nynorsk, no=Both -->
1065 </analyzer>
1066 </fieldType>
1067
1068 <!-- Portuguese -->
1069 <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
1070 <analyzer>
1071 <tokenizer class="solr.StandardTokenizerFactory"/>
1072 <filter class="solr.LowerCaseFilterFactory"/>
1073 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
1074 <filter class="solr.PortugueseLightStemFilterFactory"/>
1075 <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
1076 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
1077 <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
1078 </analyzer>
1079 </fieldType>
1080
1081 <!-- Romanian -->
1082 <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
1083 <analyzer>
1084 <tokenizer class="solr.StandardTokenizerFactory"/>
1085 <filter class="solr.LowerCaseFilterFactory"/>
1086 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" />
1087 <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
1088 </analyzer>
1089 </fieldType>
1090
1091 <!-- Russian -->
1092 <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
1093 <analyzer>
1094 <tokenizer class="solr.StandardTokenizerFactory"/>
1095 <filter class="solr.LowerCaseFilterFactory"/>
1096 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
1097 <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
1098 <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
1099 </analyzer>
1100 </fieldType>
1101<!-- Russian with morphology-->
1102 <fieldType name="text_ru_morph" class="solr.TextField" positionIncrementGap="100">
1103 <analyzer>
1104 <tokenizer class="solr.StandardTokenizerFactory"/>
1105 <filter class="solr.LowerCaseFilterFactory"/>
1106 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
1107 <filter class="org.apache.lucene.morphology.russian.RussianFilterFactory"/>
1108 </analyzer>
1109 </fieldType>
1110
1111 <!-- Swedish -->
1112 <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
1113 <analyzer>
1114 <tokenizer class="solr.StandardTokenizerFactory"/>
1115 <filter class="solr.LowerCaseFilterFactory"/>
1116 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
1117 <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
1118 <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
1119 </analyzer>
1120 </fieldType>
1121
1122 <!-- Thai -->
1123 <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
1124 <analyzer>
1125 <tokenizer class="solr.StandardTokenizerFactory"/>
1126 <filter class="solr.LowerCaseFilterFactory"/>
1127 <filter class="solr.ThaiWordFilterFactory"/>
1128 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" />
1129 </analyzer>
1130 </fieldType>
1131
1132 <!-- Turkish -->
1133 <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
1134 <analyzer>
1135 <tokenizer class="solr.StandardTokenizerFactory"/>
1136 <filter class="solr.TurkishLowerCaseFilterFactory"/>
1137 <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
1138 <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
1139 </analyzer>
1140 </fieldType>
1141
1142 </types>
1143
1144 <!-- Similarity is the scoring routine for each document vs. a query.
1145 A custom Similarity or SimilarityFactory may be specified here, but
1146 the default is fine for most applications.
1147 For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
1148 -->
1149 <!--
1150 <similarity class="com.example.solr.CustomSimilarityFactory">
1151 <str name="paramkey">param value</str>
1152 </similarity>
1153 -->
1154
1155</schema>
Note: See TracBrowser for help on using the repository browser.