source: main/trunk/model-sites-dev/eurovision-lod/collect/eurovision/etc/conf/schema.xml@ 35106

Last change on this file since 35106 was 35106, checked in by davidb, 3 years ago

adjusted svn:ignore rule
File size: 62.4 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
113 <field name="docOID" type="string" indexed="true" stored="true" required="true" />
114
115 <field name="ZZ" type="text_en_splitting" indexed="true" stored="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true" />
116 <field name="TX" type="text_en_splitting" indexed="true" stored="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true" />
117 <field name="TI" type="text_en_splitting" indexed="true" stored="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true" />
118 <field name="CR" type="text_en_splitting" indexed="true" stored="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true" />
119 <field name="CU" type="text_en_splitting" indexed="true" stored="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true" />
120 <field name="YE" type="text_en_splitting" indexed="true" stored="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true" />
121
122
123 <field name="_version_" type="long" indexed="true" stored="true"/>
124
125 <!-- points to the root document of a block of nested documents. Required for nested
126 document support, may be removed otherwise
127 -->
128 <field name="_root_" type="string" indexed="true" stored="false"/>
129
130 <!-- Only remove the "id" field if you have a very good reason to. While not strictly
131 required, it is highly recommended. A <uniqueKey> is present in almost all Solr
132 installations. See the <uniqueKey> declaration below where <uniqueKey> is set to "id".
133 -->
134<!--
135 <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
136-->
137
138<!--
139 <field name="sku" type="text_en_splitting_tight" indexed="true" stored="true" omitNorms="true"/>
140 <field name="name" type="text_general" indexed="true" stored="true"/>
141 <field name="manu" type="text_general" indexed="true" stored="true" omitNorms="true"/>
142 <field name="cat" type="string" indexed="true" stored="true" multiValued="true"/>
143 <field name="features" type="text_general" indexed="true" stored="true" multiValued="true"/>
144 <field name="includes" type="text_general" indexed="true" stored="true" termVectors="true" termPositions="true" termOffsets="true" />
145
146 <field name="weight" type="float" indexed="true" stored="true"/>
147 <field name="price" type="float" indexed="true" stored="true"/>
148 <field name="popularity" type="int" indexed="true" stored="true" />
149 <field name="inStock" type="boolean" indexed="true" stored="true" />
150-->
151 <field name="store" type="location" indexed="true" stored="true"/>
152
153 <!-- Common metadata fields, named specifically to match up with
154 SolrCell metadata when parsing rich documents such as Word, PDF.
155 Some fields are multiValued only because Tika currently may return
156 multiple values for them. Some metadata is parsed from the documents,
157 but there are some which come from the client context:
158 "content_type": From the HTTP headers of incoming stream
159 "resourcename": From SolrCell request param resource.name
160 -->
161
162<!--
163 <field name="title" type="text_general" indexed="true" stored="true" multiValued="true"/>
164 <field name="subject" type="text_general" indexed="true" stored="true"/>
165 <field name="description" type="text_general" indexed="true" stored="true"/>
166 <field name="comments" type="text_general" indexed="true" stored="true"/>
167 <field name="author" type="text_general" indexed="true" stored="true"/>
168 <field name="keywords" type="text_general" indexed="true" stored="true"/>
169 <field name="category" type="text_general" indexed="true" stored="true"/>
170 <field name="resourcename" type="text_general" indexed="true" stored="true"/>
171 <field name="url" type="text_general" indexed="true" stored="true"/>
172 <field name="content_type" type="string" indexed="true" stored="true" multiValued="true"/>
173 <field name="last_modified" type="date" indexed="true" stored="true"/>
174 <field name="links" type="string" indexed="true" stored="true" multiValued="true"/>
175-->
176
177 <!-- Main body of document extracted by SolrCell.
178 NOTE: This field is not indexed by default, since it is also copied to "text"
179 using copyField below. This is to save space. Use this field for returning and
180 highlighting document content. Use the "text" field to search the content. -->
181 <field name="content" type="text_general" indexed="false" stored="true" multiValued="true"/>
182
183
184 <!-- catchall field, containing all other searchable text fields (implemented
185 via copyField further on in this schema -->
186 <field name="text" type="text_general" indexed="true" stored="false" multiValued="true"/>
187
188 <!-- catchall text field that indexes tokens both normally and in reverse for efficient
189 leading wildcard queries. -->
190 <field name="text_rev" type="text_general_rev" indexed="true" stored="false" multiValued="true"/>
191
192 <!-- non-tokenized version of manufacturer to make it easier to sort or group
193 results by manufacturer. copied from "manu" via copyField -->
194 <field name="manu_exact" type="string" indexed="true" stored="false"/>
195
196 <field name="payloads" type="payloads" indexed="true" stored="true"/>
197
198
199 <!--
200 Some fields such as popularity and manu_exact could be modified to
201 leverage doc values:
202 <field name="popularity" type="int" indexed="true" stored="true" docValues="true" />
203 <field name="manu_exact" type="string" indexed="false" stored="false" docValues="true" />
204 <field name="cat" type="string" indexed="true" stored="true" docValues="true" multiValued="true"/>
205
206
207 Although it would make indexing slightly slower and the index bigger, it
208 would also make the index faster to load, more memory-efficient and more
209 NRT-friendly.
210 -->
211
212 <!-- Dynamic field definitions allow using convention over configuration
213 for fields via the specification of patterns to match field names.
214 EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
215 RESTRICTION: the glob-like pattern in the name attribute must have
216 a "*" only at the start or the end. -->
217
218 <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
219 <dynamicField name="*_is" type="int" indexed="true" stored="true" multiValued="true"/>
220 <dynamicField name="*_s" type="string" indexed="true" stored="true" />
221 <dynamicField name="*_ss" type="string" indexed="true" stored="true" multiValued="true"/>
222 <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
223 <dynamicField name="*_ls" type="long" indexed="true" stored="true" multiValued="true"/>
224 <dynamicField name="*_t" type="text_general" indexed="true" stored="true"/>
225 <dynamicField name="*_txt" type="text_general" indexed="true" stored="true" multiValued="true"/>
226 <dynamicField name="*_en" type="text_en" indexed="true" stored="true" multiValued="true"/>
227 <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
228 <dynamicField name="*_bs" type="boolean" indexed="true" stored="true" multiValued="true"/>
229 <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
230 <dynamicField name="*_fs" type="float" indexed="true" stored="true" multiValued="true"/>
231 <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
232 <dynamicField name="*_ds" type="double" indexed="true" stored="true" multiValued="true"/>
233
234 <!-- Type used to index the lat and lon components for the "location" FieldType -->
235 <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false" />
236
237 <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
238 <dynamicField name="*_dts" type="date" indexed="true" stored="true" multiValued="true"/>
239 <dynamicField name="*_p" type="location" indexed="true" stored="true"/>
240
241 <!-- some trie-coded dynamic fields for faster range queries -->
242 <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
243 <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
244 <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
245 <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
246 <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
247
248 <dynamicField name="*_pi" type="pint" indexed="true" stored="true"/>
249 <dynamicField name="*_c" type="currency" indexed="true" stored="true"/>
250
251 <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
252 <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
253
254 <dynamicField name="random_*" type="random" />
255
256 <!-- dynamic field for sort/facet fields, which are strings by default. ie not tokenised -->
257 <dynamicField name="by*" type="string" indexed="true" stored="false" multiValued="false" />
258 <dynamicField name="fc*" type="string" indexed="true" stored="false" multiValued="true" />
259
260 <!-- uncomment the following to ignore any fields that don't already match an existing
261 field name or dynamic field, rather than reporting them as an error.
262 alternately, change the type="ignored" to some other type e.g. "text" if you want
263 unknown fields indexed and/or stored by default -->
264 <!--dynamicField name="*" type="ignored" multiValued="true" /-->
265
266 </fields>
267
268
269 <!-- Field to use to determine and enforce document uniqueness.
270 Unless this field is marked with required="false", it will be a required field
271 -->
272 <uniqueKey>docOID</uniqueKey>
273
274 <!-- DEPRECATED: The defaultSearchField is consulted by various query parsers when
275 parsing a query string that isn't explicit about the field. Machine (non-user)
276 generated queries are best made explicit, or they can use the "df" request parameter
277 which takes precedence over this.
278 Note: Un-commenting defaultSearchField will be insufficient if your request handler
279 in solrconfig.xml defines "df", which takes precedence. That would need to be removed.
280 <defaultSearchField>text</defaultSearchField> -->
281
282 <!-- DEPRECATED: The defaultOperator (AND|OR) is consulted by various query parsers
283 when parsing a query string to determine if a clause of the query should be marked as
284 required or optional, assuming the clause isn't already marked by some operator.
285 The default is OR, which is generally assumed so it is not a good idea to change it
286 globally here. The "q.op" request parameter takes precedence over this.
287 <solrQueryParser defaultOperator="OR"/> -->
288
289 <!-- copyField commands copy one field to another at the time a document
290 is added to the index. It's used either to index the same field differently,
291 or to add multiple fields to the same field for easier/faster searching. -->
292<!--
293 <copyField source="cat" dest="text"/>
294 <copyField source="name" dest="text"/>
295 <copyField source="manu" dest="text"/>
296 <copyField source="features" dest="text"/>
297 <copyField source="includes" dest="text"/>
298 <copyField source="manu" dest="manu_exact"/>
299-->
300
301 <!-- Copy the price into a currency enabled field (default USD) -->
302<!--
303 <copyField source="price" dest="price_c"/>
304-->
305
306 <!-- Text fields from SolrCell to search by default in our catch-all field -->
307<!--
308 <copyField source="title" dest="text"/>
309 <copyField source="author" dest="text"/>
310 <copyField source="description" dest="text"/>
311 <copyField source="keywords" dest="text"/>
312 <copyField source="content" dest="text"/>
313 <copyField source="content_type" dest="text"/>
314 <copyField source="resourcename" dest="text"/>
315 <copyField source="url" dest="text"/>
316-->
317
318 <!-- Create a string version of author for faceting -->
319<!--
320 <copyField source="author" dest="author_s"/>
321-->
322
323 <!-- Above, multiple source fields are copied to the [text] field.
324 Another way to map multiple source fields to the same
325 destination field is to use the dynamic field syntax.
326 copyField also supports a maxChars to copy setting. -->
327
328 <!-- <copyField source="*_t" dest="text" maxChars="3000"/> -->
329
330 <!-- copy name to alphaNameSort, a field designed for sorting by name -->
331 <!-- <copyField source="name" dest="alphaNameSort"/> -->
332
333 <types>
334 <!-- field type definitions. The "name" attribute is
335 just a label to be used by field definitions. The "class"
336 attribute and any other attributes determine the real
337 behavior of the fieldType.
338 Class names starting with "solr" refer to java classes in a
339 standard package such as org.apache.solr.analysis
340 -->
341
342 <!-- The StrField type is not analyzed, but indexed/stored verbatim.
343 It supports doc values but in that case the field needs to be
344 single-valued and either required or have a default value.
345 -->
346 <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
347
348 <!-- boolean type: "true" or "false" -->
349 <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
350
351 <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
352 currently supported on types that are sorted internally as strings
353 and on numeric types.
354 This includes "string","boolean", and, as of 3.5 (and 4.x),
355 int, float, long, date, double, including the "Trie" variants.
356 - If sortMissingLast="true", then a sort on this field will cause documents
357 without the field to come after documents with the field,
358 regardless of the requested sort order (asc or desc).
359 - If sortMissingFirst="true", then a sort on this field will cause documents
360 without the field to come before documents with the field,
361 regardless of the requested sort order.
362 - If sortMissingLast="false" and sortMissingFirst="false" (the default),
363 then default lucene sorting will be used which places docs without the
364 field first in an ascending sort and last in a descending sort.
365 -->
366
367 <!--
368 Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
369
370 These fields support doc values, but they require the field to be
371 single-valued and either be required or have a default value.
372 -->
373 <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
374 <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
375 <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
376 <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
377
378 <!--
379 Numeric field types that index each value at various levels of precision
380 to accelerate range queries when the number of values between the range
381 endpoints is large. See the javadoc for NumericRangeQuery for internal
382 implementation details.
383
384 Smaller precisionStep values (specified in bits) will lead to more tokens
385 indexed per value, slightly larger index size, and faster range queries.
386 A precisionStep of 0 disables indexing at different precision levels.
387 -->
388 <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
389 <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
390 <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
391 <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
392
393 <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
394 is a more restricted form of the canonical representation of dateTime
395 http://www.w3.org/TR/xmlschema-2/#dateTime
396 The trailing "Z" designates UTC time and is mandatory.
397 Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
398 All other components are mandatory.
399
400 Expressions can also be used to denote calculations that should be
401 performed relative to "NOW" to determine the value, ie...
402
403 NOW/HOUR
404 ... Round to the start of the current hour
405 NOW-1DAY
406 ... Exactly 1 day prior to now
407 NOW/DAY+6MONTHS+3DAYS
408 ... 6 months and 3 days in the future from the start of
409 the current day
410
411 Consult the DateField javadocs for more information.
412
413 Note: For faster range queries, consider the tdate type
414 -->
415 <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
416
417 <!-- A Trie based date field for faster date range queries and date faceting. -->
418 <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
419
420
421 <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
422 <fieldtype name="binary" class="solr.BinaryField"/>
423
424 <!--
425 Note:
426 These should only be used for compatibility with existing indexes (created with lucene or older Solr versions).
427 Use Trie based fields instead. As of Solr 3.5 and 4.x, Trie based fields support sortMissingFirst/Last
428
429 Plain numeric field types that store and index the text
430 value verbatim (and hence don't correctly support range queries, since the
431 lexicographic ordering isn't equal to the numeric ordering)
432 -->
433 <fieldType name="pint" class="solr.IntField"/>
434 <fieldType name="plong" class="solr.LongField"/>
435 <fieldType name="pfloat" class="solr.FloatField"/>
436 <fieldType name="pdouble" class="solr.DoubleField"/>
437 <fieldType name="pdate" class="solr.DateField" sortMissingLast="true"/>
438
439 <!-- The "RandomSortField" is not used to store or search any
440 data. You can declare fields of this type it in your schema
441 to generate pseudo-random orderings of your docs for sorting
442 or function purposes. The ordering is generated based on the field
443 name and the version of the index. As long as the index version
444 remains unchanged, and the same field name is reused,
445 the ordering of the docs will be consistent.
446 If you want different psuedo-random orderings of documents,
447 for the same version of the index, use a dynamicField and
448 change the field name in the request.
449 -->
450 <fieldType name="random" class="solr.RandomSortField" indexed="true" />
451
452 <!-- solr.TextField allows the specification of custom text analyzers
453 specified as a tokenizer and a list of token filters. Different
454 analyzers may be specified for indexing and querying.
455
456 The optional positionIncrementGap puts space between multiple fields of
457 this type on the same document, with the purpose of preventing false phrase
458 matching across fields.
459
460 For more info on customizing your analyzer chain, please see
461 http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
462 -->
463
464 <!-- One can also specify an existing Analyzer class that has a
465 default constructor via the class attribute on the analyzer element.
466 Example:
467 <fieldType name="text_greek" class="solr.TextField">
468 <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
469 </fieldType>
470 -->
471
472 <!-- A text field that only splits on whitespace for exact matching of words -->
473 <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
474 <analyzer>
475 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
476 </analyzer>
477 </fieldType>
478
479 <!-- A general text field that has reasonable, generic
480 cross-language defaults: it tokenizes with StandardTokenizer,
481 removes stop words from case-insensitive "stopwords.txt"
482 (empty by default), and down cases. At query time only, it
483 also applies synonyms. -->
484 <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
485 <analyzer type="index">
486 <charFilter class="solr.HTMLStripCharFilterFactory"/>
487 <tokenizer class="solr.StandardTokenizerFactory"/>
488 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
489 <!-- in this example, we will only use synonyms at query time
490 <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
491 -->
492 <filter class="solr.LowerCaseFilterFactory"/>
493 </analyzer>
494 <analyzer type="query">
495 <tokenizer class="solr.StandardTokenizerFactory"/>
496 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
497 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
498 <filter class="solr.LowerCaseFilterFactory"/>
499 </analyzer>
500 </fieldType>
501
502 <!-- A text field with defaults appropriate for English: it
503 tokenizes with StandardTokenizer, removes English stop words
504 (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
505 finally applies Porter's stemming. The query time analyzer
506 also applies synonyms from synonyms.txt. -->
507 <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
508 <analyzer type="index">
509 <charFilter class="solr.HTMLStripCharFilterFactory"/>
510 <tokenizer class="solr.StandardTokenizerFactory"/>
511 <!-- in this example, we will only use synonyms at query time
512 <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
513 -->
514 <!-- Case insensitive stop word removal.
515 -->
516 <filter class="solr.StopFilterFactory"
517 ignoreCase="true"
518 words="lang/stopwords_en.txt"
519 />
520 <filter class="solr.LowerCaseFilterFactory"/>
521 <filter class="solr.EnglishPossessiveFilterFactory"/>
522 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
523 <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
524 <filter class="solr.EnglishMinimalStemFilterFactory"/>
525 -->
526 <!--<filter class="solr.PorterStemFilterFactory"/>-->
527 <filter class="solr.EnglishMinimalStemFilterFactory"/>
528 </analyzer>
529 <analyzer type="query">
530 <tokenizer class="solr.StandardTokenizerFactory"/>
531 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
532 <filter class="solr.StopFilterFactory"
533 ignoreCase="true"
534 words="lang/stopwords_en.txt"
535 />
536 <filter class="solr.LowerCaseFilterFactory"/>
537 <filter class="solr.EnglishPossessiveFilterFactory"/>
538 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
539 <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
540 <filter class="solr.EnglishMinimalStemFilterFactory"/>
541 -->
542 <!--<filter class="solr.PorterStemFilterFactory"/>-->
543 <filter class="solr.EnglishMinimalStemFilterFactory"/>
544 </analyzer>
545 </fieldType>
546
547 <!-- A text field with defaults appropriate for English, plus
548 aggressive word-splitting and autophrase features enabled.
549 This field is just like text_en, except it adds
550 WordDelimiterFilter to enable splitting and matching of
551 words on case-change, alpha numeric boundaries, and
552 non-alphanumeric chars. This means certain compound word
553 cases will work, for example query "wi fi" will match
554 document "WiFi" or "wi-fi".
555 -->
556 <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
557 <analyzer type="index">
558 <charFilter class="solr.HTMLStripCharFilterFactory"/>
559 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
560 <!-- in this example, we will only use synonyms at query time
561 <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
562 -->
563 <!-- Case insensitive stop word removal.
564 -->
565 <filter class="solr.StopFilterFactory"
566 ignoreCase="true"
567 words="lang/stopwords_en.txt"
568 />
569 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
570 <filter class="solr.LowerCaseFilterFactory"/>
571 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
572 <!--<filter class="solr.PorterStemFilterFactory"/>-->
573 <filter class="solr.EnglishMinimalStemFilterFactory"/>
574 </analyzer>
575 <analyzer type="query">
576 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
577 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
578 <filter class="solr.StopFilterFactory"
579 ignoreCase="true"
580 words="lang/stopwords_en.txt"
581 />
582 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
583 <filter class="solr.LowerCaseFilterFactory"/>
584 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
585 <!--<filter class="solr.PorterStemFilterFactory"/>-->
586 <filter class="solr.EnglishMinimalStemFilterFactory"/>
587 </analyzer>
588 </fieldType>
589
590 <!-- Less flexible matching, but less false matches. Probably not ideal for product names,
591 but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
592 <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
593 <analyzer>
594 <charFilter class="solr.HTMLStripCharFilterFactory"/>
595 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
596 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
597 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
598 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
599 <filter class="solr.LowerCaseFilterFactory"/>
600 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
601 <filter class="solr.EnglishMinimalStemFilterFactory"/>
602 <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
603 possible with WordDelimiterFilter in conjuncton with stemming. -->
604 <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
605 </analyzer>
606 </fieldType>
607
608 <!-- Just like text_general except it reverses the characters of
609 each token, to enable more efficient leading wildcard queries. -->
610 <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
611 <analyzer type="index">
612 <tokenizer class="solr.StandardTokenizerFactory"/>
613 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
614 <filter class="solr.LowerCaseFilterFactory"/>
615 <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
616 maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
617 </analyzer>
618 <analyzer type="query">
619 <tokenizer class="solr.StandardTokenizerFactory"/>
620 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
621 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
622 <filter class="solr.LowerCaseFilterFactory"/>
623 </analyzer>
624 </fieldType>
625
626 <!-- charFilter + WhitespaceTokenizer -->
627 <!--
628 <fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
629 <analyzer>
630 <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
631 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
632 </analyzer>
633 </fieldType>
634 -->
635
636 <!-- This is an example of using the KeywordTokenizer along
637 With various TokenFilterFactories to produce a sortable field
638 that does not include some properties of the source text
639 -->
640 <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
641 <analyzer>
642 <!-- KeywordTokenizer does no actual tokenizing, so the entire
643 input string is preserved as a single token
644 -->
645 <tokenizer class="solr.KeywordTokenizerFactory"/>
646 <!-- The LowerCase TokenFilter does what you expect, which can be
647 when you want your sorting to be case insensitive
648 -->
649 <filter class="solr.LowerCaseFilterFactory" />
650 <!-- The TrimFilter removes any leading or trailing whitespace -->
651 <filter class="solr.TrimFilterFactory" />
652 <!-- The PatternReplaceFilter gives you the flexibility to use
653 Java Regular expression to replace any sequence of characters
654 matching a pattern with an arbitrary replacement string,
655 which may include back references to portions of the original
656 string matched by the pattern.
657
658 See the Java Regular Expression documentation for more
659 information on pattern and replacement string syntax.
660
661 http://java.sun.com/j2se/1.6.0/docs/api/java/util/regex/package-summary.html
662 -->
663 <filter class="solr.PatternReplaceFilterFactory"
664 pattern="([^a-z])" replacement="" replace="all"
665 />
666 </analyzer>
667 </fieldType>
668
669 <fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
670 <analyzer>
671 <tokenizer class="solr.StandardTokenizerFactory"/>
672 <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
673 </analyzer>
674 </fieldtype>
675
676 <fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
677 <analyzer>
678 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
679 <!--
680 The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
681 a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
682 Attributes of the DelimitedPayloadTokenFilterFactory :
683 "delimiter" - a one character delimiter. Default is | (pipe)
684 "encoder" - how to encode the following value into a playload
685 float -> org.apache.lucene.analysis.payloads.FloatEncoder,
686 integer -> o.a.l.a.p.IntegerEncoder
687 identity -> o.a.l.a.p.IdentityEncoder
688 Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
689 -->
690 <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
691 </analyzer>
692 </fieldtype>
693
694 <!-- lowercases the entire field value, keeping it as a single token. -->
695 <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
696 <analyzer>
697 <tokenizer class="solr.KeywordTokenizerFactory"/>
698 <filter class="solr.LowerCaseFilterFactory" />
699 </analyzer>
700 </fieldType>
701
702 <!--
703 Example of using PathHierarchyTokenizerFactory at index time, so
704 queries for paths match documents at that path, or in descendent paths
705 -->
706 <fieldType name="descendent_path" class="solr.TextField">
707 <analyzer type="index">
708 <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
709 </analyzer>
710 <analyzer type="query">
711 <tokenizer class="solr.KeywordTokenizerFactory" />
712 </analyzer>
713 </fieldType>
714 <!--
715 Example of using PathHierarchyTokenizerFactory at query time, so
716 queries for paths match documents at that path, or in ancestor paths
717 -->
718 <fieldType name="ancestor_path" class="solr.TextField">
719 <analyzer type="index">
720 <tokenizer class="solr.KeywordTokenizerFactory" />
721 </analyzer>
722 <analyzer type="query">
723 <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
724 </analyzer>
725 </fieldType>
726
727 <!-- since fields of this type are by default not stored or indexed,
728 any data added to them will be ignored outright. -->
729 <fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
730
731 <!-- This point type indexes the coordinates as separate fields (subFields)
732 If subFieldType is defined, it references a type, and a dynamic field
733 definition is created matching *___<typename>. Alternately, if
734 subFieldSuffix is defined, that is used to create the subFields.
735 Example: if subFieldType="double", then the coordinates would be
736 indexed in fields myloc_0___double,myloc_1___double.
737 Example: if subFieldSuffix="_d" then the coordinates would be indexed
738 in fields myloc_0_d,myloc_1_d
739 The subFields are an implementation detail of the fieldType, and end
740 users normally should not need to know about them.
741 -->
742 <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
743
744 <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
745 <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
746
747 <!-- An alternative geospatial field type new to Solr 4. It supports multiValued and polygon shapes.
748 For more information about this and other Spatial fields new to Solr 4, see:
749 http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
750 -->
751 <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
752 geo="true" distErrPct="0.025" maxDistErr="0.000009" units="degrees" />
753
754 <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
755 Parameters:
756 defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
757 precisionStep: Specifies the precisionStep for the TrieLong field used for the amount
758 providerClass: Lets you plug in other exchange provider backend:
759 solr.FileExchangeRateProvider is the default and takes one parameter:
760 currencyConfig: name of an xml file holding exchange rates
761 solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
762 ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
763 refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
764 -->
765 <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
766
767
768
769 <!-- some examples for different languages (generally ordered by ISO code) -->
770
771 <!-- Arabic -->
772 <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
773 <analyzer>
774 <charFilter class="solr.HTMLStripCharFilterFactory"/>
775 <tokenizer class="solr.StandardTokenizerFactory"/>
776 <!-- for any non-arabic -->
777 <filter class="solr.LowerCaseFilterFactory"/>
778 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
779 <!-- normalizes ﻯ to ﻱ, etc -->
780 <filter class="solr.ArabicNormalizationFilterFactory"/>
781 <filter class="solr.ArabicStemFilterFactory"/>
782 </analyzer>
783 </fieldType>
784
785 <!-- Bulgarian -->
786 <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
787 <analyzer>
788 <charFilter class="solr.HTMLStripCharFilterFactory"/>
789 <tokenizer class="solr.StandardTokenizerFactory"/>
790 <filter class="solr.LowerCaseFilterFactory"/>
791 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" />
792 <filter class="solr.BulgarianStemFilterFactory"/>
793 </analyzer>
794 </fieldType>
795
796 <!-- Catalan -->
797 <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
798 <analyzer>
799 <charFilter class="solr.HTMLStripCharFilterFactory"/>
800 <tokenizer class="solr.StandardTokenizerFactory"/>
801 <!-- removes l', etc -->
802 <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
803 <filter class="solr.LowerCaseFilterFactory"/>
804 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" />
805 <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
806 </analyzer>
807 </fieldType>
808
809 <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
810 <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
811 <analyzer>
812 <charFilter class="solr.HTMLStripCharFilterFactory"/>
813 <tokenizer class="solr.StandardTokenizerFactory"/>
814 <!-- normalize width before bigram, as e.g. half-width dakuten combine -->
815 <filter class="solr.CJKWidthFilterFactory"/>
816 <!-- for any non-CJK -->
817 <filter class="solr.LowerCaseFilterFactory"/>
818 <filter class="solr.CJKBigramFilterFactory"/>
819 </analyzer>
820 </fieldType>
821
822 <!-- Kurdish -->
823 <fieldType name="text_ckb" class="solr.TextField" positionIncrementGap="100">
824 <analyzer>
825 <charFilter class="solr.HTMLStripCharFilterFactory"/>
826 <tokenizer class="solr.StandardTokenizerFactory"/>
827 <filter class="solr.SoraniNormalizationFilterFactory"/>
828 <!-- for any latin text -->
829 <filter class="solr.LowerCaseFilterFactory"/>
830 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ckb.txt"/>
831 <filter class="solr.SoraniStemFilterFactory"/>
832 </analyzer>
833 </fieldType>
834
835 <!-- Czech -->
836 <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
837 <analyzer>
838 <charFilter class="solr.HTMLStripCharFilterFactory"/>
839 <tokenizer class="solr.StandardTokenizerFactory"/>
840 <filter class="solr.LowerCaseFilterFactory"/>
841 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" />
842 <filter class="solr.CzechStemFilterFactory"/>
843 </analyzer>
844 </fieldType>
845
846 <!-- Danish -->
847 <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
848 <analyzer>
849 <charFilter class="solr.HTMLStripCharFilterFactory"/>
850 <tokenizer class="solr.StandardTokenizerFactory"/>
851 <filter class="solr.LowerCaseFilterFactory"/>
852 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
853 <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
854 </analyzer>
855 </fieldType>
856
857 <!-- German -->
858 <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
859 <analyzer>
860 <charFilter class="solr.HTMLStripCharFilterFactory"/>
861 <tokenizer class="solr.StandardTokenizerFactory"/>
862 <filter class="solr.LowerCaseFilterFactory"/>
863 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" />
864 <filter class="solr.GermanNormalizationFilterFactory"/>
865 <filter class="solr.GermanLightStemFilterFactory"/>
866 <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
867 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
868 </analyzer>
869 </fieldType>
870
871 <!-- Greek -->
872 <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
873 <analyzer>
874 <charFilter class="solr.HTMLStripCharFilterFactory"/>
875 <tokenizer class="solr.StandardTokenizerFactory"/>
876 <!-- greek specific lowercase for sigma -->
877 <filter class="solr.GreekLowerCaseFilterFactory"/>
878 <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
879 <filter class="solr.GreekStemFilterFactory"/>
880 </analyzer>
881 </fieldType>
882
883 <!-- Spanish -->
884 <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
885 <analyzer>
886 <charFilter class="solr.HTMLStripCharFilterFactory"/>
887 <tokenizer class="solr.StandardTokenizerFactory"/>
888 <filter class="solr.LowerCaseFilterFactory"/>
889 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
890 <filter class="solr.SpanishLightStemFilterFactory"/>
891 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
892 </analyzer>
893 </fieldType>
894
895 <!-- Basque -->
896 <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
897 <analyzer>
898 <charFilter class="solr.HTMLStripCharFilterFactory"/>
899 <tokenizer class="solr.StandardTokenizerFactory"/>
900 <filter class="solr.LowerCaseFilterFactory"/>
901 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" />
902 <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
903 </analyzer>
904 </fieldType>
905
906 <!-- Persian -->
907 <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
908 <analyzer>
909 <!-- for ZWNJ -->
910 <charFilter class="solr.HTMLStripCharFilterFactory"/>
911 <charFilter class="solr.PersianCharFilterFactory"/>
912 <tokenizer class="solr.StandardTokenizerFactory"/>
913 <filter class="solr.LowerCaseFilterFactory"/>
914 <filter class="solr.ArabicNormalizationFilterFactory"/>
915 <filter class="solr.PersianNormalizationFilterFactory"/>
916 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" />
917 </analyzer>
918 </fieldType>
919
920 <!-- Finnish -->
921 <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
922 <analyzer>
923 <charFilter class="solr.HTMLStripCharFilterFactory"/>
924 <tokenizer class="solr.StandardTokenizerFactory"/>
925 <filter class="solr.LowerCaseFilterFactory"/>
926 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
927 <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
928 <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
929 </analyzer>
930 </fieldType>
931
932 <!-- French -->
933 <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
934 <analyzer>
935 <charFilter class="solr.HTMLStripCharFilterFactory"/>
936 <tokenizer class="solr.StandardTokenizerFactory"/>
937 <!-- removes l', etc -->
938 <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
939 <filter class="solr.LowerCaseFilterFactory"/>
940 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
941 <filter class="solr.FrenchLightStemFilterFactory"/>
942 <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
943 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
944 </analyzer>
945 </fieldType>
946
947 <!-- Irish -->
948 <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
949 <analyzer>
950 <charFilter class="solr.HTMLStripCharFilterFactory"/>
951 <tokenizer class="solr.StandardTokenizerFactory"/>
952 <!-- removes d', etc -->
953 <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
954 <!-- removes n-, etc. position increments is intentionally false! -->
955 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
956 <filter class="solr.IrishLowerCaseFilterFactory"/>
957 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/>
958 <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
959 </analyzer>
960 </fieldType>
961
962 <!-- Galician -->
963 <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
964 <analyzer>
965 <charFilter class="solr.HTMLStripCharFilterFactory"/>
966 <tokenizer class="solr.StandardTokenizerFactory"/>
967 <filter class="solr.LowerCaseFilterFactory"/>
968 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" />
969 <filter class="solr.GalicianStemFilterFactory"/>
970 <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
971 </analyzer>
972 </fieldType>
973
974 <!-- Hindi -->
975 <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
976 <analyzer>
977 <charFilter class="solr.HTMLStripCharFilterFactory"/>
978 <tokenizer class="solr.StandardTokenizerFactory"/>
979 <filter class="solr.LowerCaseFilterFactory"/>
980 <!-- normalizes unicode representation -->
981 <filter class="solr.IndicNormalizationFilterFactory"/>
982 <!-- normalizes variation in spelling -->
983 <filter class="solr.HindiNormalizationFilterFactory"/>
984 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
985 <filter class="solr.HindiStemFilterFactory"/>
986 </analyzer>
987 </fieldType>
988
989 <!-- Hungarian -->
990 <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
991 <analyzer>
992 <charFilter class="solr.HTMLStripCharFilterFactory"/>
993 <tokenizer class="solr.StandardTokenizerFactory"/>
994 <filter class="solr.LowerCaseFilterFactory"/>
995 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
996 <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
997 <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
998 </analyzer>
999 </fieldType>
1000
1001 <!-- Armenian -->
1002 <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
1003 <analyzer>
1004 <charFilter class="solr.HTMLStripCharFilterFactory"/>
1005 <tokenizer class="solr.StandardTokenizerFactory"/>
1006 <filter class="solr.LowerCaseFilterFactory"/>
1007 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" />
1008 <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
1009 </analyzer>
1010 </fieldType>
1011
1012 <!-- Indonesian -->
1013 <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
1014 <analyzer>
1015 <charFilter class="solr.HTMLStripCharFilterFactory"/>
1016 <tokenizer class="solr.StandardTokenizerFactory"/>
1017 <filter class="solr.LowerCaseFilterFactory"/>
1018 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" />
1019 <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
1020 <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
1021 </analyzer>
1022 </fieldType>
1023
1024 <!-- Italian -->
1025 <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
1026 <analyzer>
1027 <charFilter class="solr.HTMLStripCharFilterFactory"/>
1028 <tokenizer class="solr.StandardTokenizerFactory"/>
1029 <!-- removes l', etc -->
1030 <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
1031 <filter class="solr.LowerCaseFilterFactory"/>
1032 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
1033 <filter class="solr.ItalianLightStemFilterFactory"/>
1034 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
1035 </analyzer>
1036 </fieldType>
1037
1038 <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
1039
1040 NOTE: If you want to optimize search for precision, use default operator AND in your query
1041 parser config with <solrQueryParser defaultOperator="AND"/> further down in this file. Use
1042 OR if you would like to optimize for recall (default).
1043 -->
1044 <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
1045 <analyzer>
1046 <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
1047
1048 Kuromoji has a search mode (default) that does segmentation useful for search. A heuristic
1049 is used to segment compounds into its parts and the compound itself is kept as synonym.
1050
1051 Valid values for attribute mode are:
1052 normal: regular segmentation
1053 search: segmentation useful for search with synonyms compounds (default)
1054 extended: same as search mode, but unigrams unknown words (experimental)
1055
1056 For some applications it might be good to use search mode for indexing and normal mode for
1057 queries to reduce recall and prevent parts of compounds from being matched and highlighted.
1058 Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
1059
1060 Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
1061 model with your own entries for segmentation, part-of-speech tags and readings without a need
1062 to specify weights. Notice that user dictionaries have not been subject to extensive testing.
1063
1064 User dictionary attributes are:
1065 userDictionary: user dictionary filename
1066 userDictionaryEncoding: user dictionary encoding (default is UTF-8)
1067
1068 See lang/userdict_ja.txt for a sample user dictionary file.
1069
1070 Punctuation characters are discarded by default. Use discardPunctuation="false" to keep them.
1071
1072 See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
1073 -->
1074 <charFilter class="solr.HTMLStripCharFilterFactory"/>
1075 <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
1076 <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
1077 <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (蟞曞圢) -->
1078 <filter class="solr.JapaneseBaseFormFilterFactory"/>
1079 <!-- Removes tokens with certain part-of-speech tags -->
1080 <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
1081 <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
1082 <filter class="solr.CJKWidthFilterFactory"/>
1083 <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
1084 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" />
1085 <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
1086 <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
1087 <!-- Lower-cases romaji characters -->
1088 <filter class="solr.LowerCaseFilterFactory"/>
1089 </analyzer>
1090 </fieldType>
1091
1092 <!-- Latvian -->
1093 <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
1094 <analyzer>
1095 <charFilter class="solr.HTMLStripCharFilterFactory"/>
1096 <tokenizer class="solr.StandardTokenizerFactory"/>
1097 <filter class="solr.LowerCaseFilterFactory"/>
1098 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" />
1099 <filter class="solr.LatvianStemFilterFactory"/>
1100 </analyzer>
1101 </fieldType>
1102
1103 <!-- Dutch -->
1104 <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
1105 <analyzer>
1106 <charFilter class="solr.HTMLStripCharFilterFactory"/>
1107 <tokenizer class="solr.StandardTokenizerFactory"/>
1108 <filter class="solr.LowerCaseFilterFactory"/>
1109 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
1110 <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
1111 <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
1112 </analyzer>
1113 </fieldType>
1114
1115 <!-- Norwegian -->
1116 <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
1117 <analyzer>
1118 <charFilter class="solr.HTMLStripCharFilterFactory"/>
1119 <tokenizer class="solr.StandardTokenizerFactory"/>
1120 <filter class="solr.LowerCaseFilterFactory"/>
1121 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
1122 <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
1123 <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory" variant="nb"/> -->
1124 <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory" variant="nb"/> -->
1125 <!-- The "light" and "minimal" stemmers support variants: nb=Bokmål, nn=Nynorsk, no=Both -->
1126 </analyzer>
1127 </fieldType>
1128
1129 <!-- Portuguese -->
1130 <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
1131 <analyzer>
1132 <charFilter class="solr.HTMLStripCharFilterFactory"/>
1133 <tokenizer class="solr.StandardTokenizerFactory"/>
1134 <filter class="solr.LowerCaseFilterFactory"/>
1135 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
1136 <filter class="solr.PortugueseLightStemFilterFactory"/>
1137 <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
1138 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
1139 <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
1140 </analyzer>
1141 </fieldType>
1142
1143 <!-- Romanian -->
1144 <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
1145 <analyzer>
1146 <charFilter class="solr.HTMLStripCharFilterFactory"/>
1147 <tokenizer class="solr.StandardTokenizerFactory"/>
1148 <filter class="solr.LowerCaseFilterFactory"/>
1149 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" />
1150 <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
1151 </analyzer>
1152 </fieldType>
1153
1154 <!-- Russian -->
1155 <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
1156 <analyzer>
1157 <charFilter class="solr.HTMLStripCharFilterFactory"/>
1158 <tokenizer class="solr.StandardTokenizerFactory"/>
1159 <filter class="solr.LowerCaseFilterFactory"/>
1160 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
1161 <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
1162 <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
1163 </analyzer>
1164 </fieldType>
1165 <!-- Russian with morphology-->
1166 <fieldType name="text_ru_morph" class="solr.TextField" positionIncrementGap="100">
1167 <analyzer>
1168 <charFilter class="solr.HTMLStripCharFilterFactory"/>
1169 <tokenizer class="solr.StandardTokenizerFactory"/>
1170 <filter class="solr.LowerCaseFilterFactory"/>
1171 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
1172 <filter class="company.evo.jmorphy2.lucene.Jmorphy2StemFilterFactory" dict="lang/pymorphy2_dicts"/>
1173 </analyzer>
1174 </fieldType>
1175
1176 <!-- Swedish -->
1177 <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
1178 <analyzer>
1179 <charFilter class="solr.HTMLStripCharFilterFactory"/>
1180 <tokenizer class="solr.StandardTokenizerFactory"/>
1181 <filter class="solr.LowerCaseFilterFactory"/>
1182 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
1183 <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
1184 <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
1185 </analyzer>
1186 </fieldType>
1187
1188 <!-- Thai -->
1189 <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
1190 <analyzer>
1191 <charFilter class="solr.HTMLStripCharFilterFactory"/>
1192 <tokenizer class="solr.StandardTokenizerFactory"/>
1193 <filter class="solr.LowerCaseFilterFactory"/>
1194 <filter class="solr.ThaiWordFilterFactory"/>
1195 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" />
1196 </analyzer>
1197 </fieldType>
1198
1199 <!-- Turkish -->
1200 <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
1201 <analyzer>
1202 <charFilter class="solr.HTMLStripCharFilterFactory"/>
1203 <tokenizer class="solr.StandardTokenizerFactory"/>
1204 <filter class="solr.TurkishLowerCaseFilterFactory"/>
1205 <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
1206 <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
1207 </analyzer>
1208 </fieldType>
1209
1210 </types>
1211
1212 <!-- Similarity is the scoring routine for each document vs. a query.
1213 A custom Similarity or SimilarityFactory may be specified here, but
1214 the default is fine for most applications.
1215 For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
1216 -->
1217 <!--
1218 <similarity class="com.example.solr.CustomSimilarityFactory">
1219 <str name="paramkey">param value</str>
1220 </similarity>
1221 -->
1222
1223</schema>
Note: See TracBrowser for help on using the repository browser.