source: main/trunk/model-sites-dev/eurovision-lod/collect/eurovision/etc/conf/schema.xml@ 36019

Last change on this file since 36019 was 36019, checked in by davidb, 2 years ago

Newer indexes (auto) added in
File size: 62.6 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="TI" type="text_en_splitting" indexed="true" stored="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true" />
117 <field name="CR" type="text_en_splitting" indexed="true" stored="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true" />
118 <field name="TT" 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 <field name="LY" type="text_en_splitting" indexed="true" stored="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true" />
122
123
124 <field name="_version_" type="long" indexed="true" stored="true"/>
125
126 <!-- points to the root document of a block of nested documents. Required for nested
127 document support, may be removed otherwise
128 -->
129 <field name="_root_" type="string" indexed="true" stored="false"/>
130
131 <!-- Only remove the "id" field if you have a very good reason to. While not strictly
132 required, it is highly recommended. A <uniqueKey> is present in almost all Solr
133 installations. See the <uniqueKey> declaration below where <uniqueKey> is set to "id".
134 -->
135<!--
136 <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
137-->
138
139<!--
140 <field name="sku" type="text_en_splitting_tight" indexed="true" stored="true" omitNorms="true"/>
141 <field name="name" type="text_general" indexed="true" stored="true"/>
142 <field name="manu" type="text_general" indexed="true" stored="true" omitNorms="true"/>
143 <field name="cat" type="string" indexed="true" stored="true" multiValued="true"/>
144 <field name="features" type="text_general" indexed="true" stored="true" multiValued="true"/>
145 <field name="includes" type="text_general" indexed="true" stored="true" termVectors="true" termPositions="true" termOffsets="true" />
146
147 <field name="weight" type="float" indexed="true" stored="true"/>
148 <field name="price" type="float" indexed="true" stored="true"/>
149 <field name="popularity" type="int" indexed="true" stored="true" />
150 <field name="inStock" type="boolean" indexed="true" stored="true" />
151-->
152 <field name="store" type="location" indexed="true" stored="true"/>
153
154 <!-- Common metadata fields, named specifically to match up with
155 SolrCell metadata when parsing rich documents such as Word, PDF.
156 Some fields are multiValued only because Tika currently may return
157 multiple values for them. Some metadata is parsed from the documents,
158 but there are some which come from the client context:
159 "content_type": From the HTTP headers of incoming stream
160 "resourcename": From SolrCell request param resource.name
161 -->
162
163<!--
164 <field name="title" type="text_general" indexed="true" stored="true" multiValued="true"/>
165 <field name="subject" type="text_general" indexed="true" stored="true"/>
166 <field name="description" type="text_general" indexed="true" stored="true"/>
167 <field name="comments" type="text_general" indexed="true" stored="true"/>
168 <field name="author" type="text_general" indexed="true" stored="true"/>
169 <field name="keywords" type="text_general" indexed="true" stored="true"/>
170 <field name="category" type="text_general" indexed="true" stored="true"/>
171 <field name="resourcename" type="text_general" indexed="true" stored="true"/>
172 <field name="url" type="text_general" indexed="true" stored="true"/>
173 <field name="content_type" type="string" indexed="true" stored="true" multiValued="true"/>
174 <field name="last_modified" type="date" indexed="true" stored="true"/>
175 <field name="links" type="string" indexed="true" stored="true" multiValued="true"/>
176-->
177
178 <!-- Main body of document extracted by SolrCell.
179 NOTE: This field is not indexed by default, since it is also copied to "text"
180 using copyField below. This is to save space. Use this field for returning and
181 highlighting document content. Use the "text" field to search the content. -->
182 <field name="content" type="text_general" indexed="false" stored="true" multiValued="true"/>
183
184
185 <!-- catchall field, containing all other searchable text fields (implemented
186 via copyField further on in this schema -->
187 <field name="text" type="text_general" indexed="true" stored="false" multiValued="true"/>
188
189 <!-- catchall text field that indexes tokens both normally and in reverse for efficient
190 leading wildcard queries. -->
191 <field name="text_rev" type="text_general_rev" indexed="true" stored="false" multiValued="true"/>
192
193 <!-- non-tokenized version of manufacturer to make it easier to sort or group
194 results by manufacturer. copied from "manu" via copyField -->
195 <field name="manu_exact" type="string" indexed="true" stored="false"/>
196
197 <field name="payloads" type="payloads" indexed="true" stored="true"/>
198
199
200 <!--
201 Some fields such as popularity and manu_exact could be modified to
202 leverage doc values:
203 <field name="popularity" type="int" indexed="true" stored="true" docValues="true" />
204 <field name="manu_exact" type="string" indexed="false" stored="false" docValues="true" />
205 <field name="cat" type="string" indexed="true" stored="true" docValues="true" multiValued="true"/>
206
207
208 Although it would make indexing slightly slower and the index bigger, it
209 would also make the index faster to load, more memory-efficient and more
210 NRT-friendly.
211 -->
212
213 <!-- Dynamic field definitions allow using convention over configuration
214 for fields via the specification of patterns to match field names.
215 EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
216 RESTRICTION: the glob-like pattern in the name attribute must have
217 a "*" only at the start or the end. -->
218
219 <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
220 <dynamicField name="*_is" type="int" indexed="true" stored="true" multiValued="true"/>
221 <dynamicField name="*_s" type="string" indexed="true" stored="true" />
222 <dynamicField name="*_ss" type="string" indexed="true" stored="true" multiValued="true"/>
223 <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
224 <dynamicField name="*_ls" type="long" indexed="true" stored="true" multiValued="true"/>
225 <dynamicField name="*_t" type="text_general" indexed="true" stored="true"/>
226 <dynamicField name="*_txt" type="text_general" indexed="true" stored="true" multiValued="true"/>
227 <dynamicField name="*_en" type="text_en" indexed="true" stored="true" multiValued="true"/>
228 <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
229 <dynamicField name="*_bs" type="boolean" indexed="true" stored="true" multiValued="true"/>
230 <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
231 <dynamicField name="*_fs" type="float" indexed="true" stored="true" multiValued="true"/>
232 <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
233 <dynamicField name="*_ds" type="double" indexed="true" stored="true" multiValued="true"/>
234
235 <!-- Type used to index the lat and lon components for the "location" FieldType -->
236 <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false" />
237
238 <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
239 <dynamicField name="*_dts" type="date" indexed="true" stored="true" multiValued="true"/>
240 <dynamicField name="*_p" type="location" indexed="true" stored="true"/>
241
242 <!-- some trie-coded dynamic fields for faster range queries -->
243 <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
244 <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
245 <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
246 <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
247 <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
248
249 <dynamicField name="*_pi" type="pint" indexed="true" stored="true"/>
250 <dynamicField name="*_c" type="currency" indexed="true" stored="true"/>
251
252 <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
253 <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
254
255 <dynamicField name="random_*" type="random" />
256
257 <!-- dynamic field for sort/facet fields, which are strings by default. ie not tokenised -->
258 <dynamicField name="by*" type="string" indexed="true" stored="false" multiValued="false" />
259 <dynamicField name="fc*" type="string" indexed="true" stored="false" multiValued="true" />
260
261 <!-- uncomment the following to ignore any fields that don't already match an existing
262 field name or dynamic field, rather than reporting them as an error.
263 alternately, change the type="ignored" to some other type e.g. "text" if you want
264 unknown fields indexed and/or stored by default -->
265 <!--dynamicField name="*" type="ignored" multiValued="true" /-->
266
267 </fields>
268
269
270 <!-- Field to use to determine and enforce document uniqueness.
271 Unless this field is marked with required="false", it will be a required field
272 -->
273 <uniqueKey>docOID</uniqueKey>
274
275 <!-- DEPRECATED: The defaultSearchField is consulted by various query parsers when
276 parsing a query string that isn't explicit about the field. Machine (non-user)
277 generated queries are best made explicit, or they can use the "df" request parameter
278 which takes precedence over this.
279 Note: Un-commenting defaultSearchField will be insufficient if your request handler
280 in solrconfig.xml defines "df", which takes precedence. That would need to be removed.
281 <defaultSearchField>text</defaultSearchField> -->
282
283 <!-- DEPRECATED: The defaultOperator (AND|OR) is consulted by various query parsers
284 when parsing a query string to determine if a clause of the query should be marked as
285 required or optional, assuming the clause isn't already marked by some operator.
286 The default is OR, which is generally assumed so it is not a good idea to change it
287 globally here. The "q.op" request parameter takes precedence over this.
288 <solrQueryParser defaultOperator="OR"/> -->
289
290 <!-- copyField commands copy one field to another at the time a document
291 is added to the index. It's used either to index the same field differently,
292 or to add multiple fields to the same field for easier/faster searching. -->
293<!--
294 <copyField source="cat" dest="text"/>
295 <copyField source="name" dest="text"/>
296 <copyField source="manu" dest="text"/>
297 <copyField source="features" dest="text"/>
298 <copyField source="includes" dest="text"/>
299 <copyField source="manu" dest="manu_exact"/>
300-->
301
302 <!-- Copy the price into a currency enabled field (default USD) -->
303<!--
304 <copyField source="price" dest="price_c"/>
305-->
306
307 <!-- Text fields from SolrCell to search by default in our catch-all field -->
308<!--
309 <copyField source="title" dest="text"/>
310 <copyField source="author" dest="text"/>
311 <copyField source="description" dest="text"/>
312 <copyField source="keywords" dest="text"/>
313 <copyField source="content" dest="text"/>
314 <copyField source="content_type" dest="text"/>
315 <copyField source="resourcename" dest="text"/>
316 <copyField source="url" dest="text"/>
317-->
318
319 <!-- Create a string version of author for faceting -->
320<!--
321 <copyField source="author" dest="author_s"/>
322-->
323
324 <!-- Above, multiple source fields are copied to the [text] field.
325 Another way to map multiple source fields to the same
326 destination field is to use the dynamic field syntax.
327 copyField also supports a maxChars to copy setting. -->
328
329 <!-- <copyField source="*_t" dest="text" maxChars="3000"/> -->
330
331 <!-- copy name to alphaNameSort, a field designed for sorting by name -->
332 <!-- <copyField source="name" dest="alphaNameSort"/> -->
333
334 <types>
335 <!-- field type definitions. The "name" attribute is
336 just a label to be used by field definitions. The "class"
337 attribute and any other attributes determine the real
338 behavior of the fieldType.
339 Class names starting with "solr" refer to java classes in a
340 standard package such as org.apache.solr.analysis
341 -->
342
343 <!-- The StrField type is not analyzed, but indexed/stored verbatim.
344 It supports doc values but in that case the field needs to be
345 single-valued and either required or have a default value.
346 -->
347 <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
348
349 <!-- boolean type: "true" or "false" -->
350 <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
351
352 <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
353 currently supported on types that are sorted internally as strings
354 and on numeric types.
355 This includes "string","boolean", and, as of 3.5 (and 4.x),
356 int, float, long, date, double, including the "Trie" variants.
357 - If sortMissingLast="true", then a sort on this field will cause documents
358 without the field to come after documents with the field,
359 regardless of the requested sort order (asc or desc).
360 - If sortMissingFirst="true", then a sort on this field will cause documents
361 without the field to come before documents with the field,
362 regardless of the requested sort order.
363 - If sortMissingLast="false" and sortMissingFirst="false" (the default),
364 then default lucene sorting will be used which places docs without the
365 field first in an ascending sort and last in a descending sort.
366 -->
367
368 <!--
369 Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
370
371 These fields support doc values, but they require the field to be
372 single-valued and either be required or have a default value.
373 -->
374 <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
375 <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
376 <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
377 <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
378
379 <!--
380 Numeric field types that index each value at various levels of precision
381 to accelerate range queries when the number of values between the range
382 endpoints is large. See the javadoc for NumericRangeQuery for internal
383 implementation details.
384
385 Smaller precisionStep values (specified in bits) will lead to more tokens
386 indexed per value, slightly larger index size, and faster range queries.
387 A precisionStep of 0 disables indexing at different precision levels.
388 -->
389 <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
390 <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
391 <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
392 <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
393
394 <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
395 is a more restricted form of the canonical representation of dateTime
396 http://www.w3.org/TR/xmlschema-2/#dateTime
397 The trailing "Z" designates UTC time and is mandatory.
398 Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
399 All other components are mandatory.
400
401 Expressions can also be used to denote calculations that should be
402 performed relative to "NOW" to determine the value, ie...
403
404 NOW/HOUR
405 ... Round to the start of the current hour
406 NOW-1DAY
407 ... Exactly 1 day prior to now
408 NOW/DAY+6MONTHS+3DAYS
409 ... 6 months and 3 days in the future from the start of
410 the current day
411
412 Consult the DateField javadocs for more information.
413
414 Note: For faster range queries, consider the tdate type
415 -->
416 <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
417
418 <!-- A Trie based date field for faster date range queries and date faceting. -->
419 <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
420
421
422 <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
423 <fieldtype name="binary" class="solr.BinaryField"/>
424
425 <!--
426 Note:
427 These should only be used for compatibility with existing indexes (created with lucene or older Solr versions).
428 Use Trie based fields instead. As of Solr 3.5 and 4.x, Trie based fields support sortMissingFirst/Last
429
430 Plain numeric field types that store and index the text
431 value verbatim (and hence don't correctly support range queries, since the
432 lexicographic ordering isn't equal to the numeric ordering)
433 -->
434 <fieldType name="pint" class="solr.IntField"/>
435 <fieldType name="plong" class="solr.LongField"/>
436 <fieldType name="pfloat" class="solr.FloatField"/>
437 <fieldType name="pdouble" class="solr.DoubleField"/>
438 <fieldType name="pdate" class="solr.DateField" sortMissingLast="true"/>
439
440 <!-- The "RandomSortField" is not used to store or search any
441 data. You can declare fields of this type it in your schema
442 to generate pseudo-random orderings of your docs for sorting
443 or function purposes. The ordering is generated based on the field
444 name and the version of the index. As long as the index version
445 remains unchanged, and the same field name is reused,
446 the ordering of the docs will be consistent.
447 If you want different psuedo-random orderings of documents,
448 for the same version of the index, use a dynamicField and
449 change the field name in the request.
450 -->
451 <fieldType name="random" class="solr.RandomSortField" indexed="true" />
452
453 <!-- solr.TextField allows the specification of custom text analyzers
454 specified as a tokenizer and a list of token filters. Different
455 analyzers may be specified for indexing and querying.
456
457 The optional positionIncrementGap puts space between multiple fields of
458 this type on the same document, with the purpose of preventing false phrase
459 matching across fields.
460
461 For more info on customizing your analyzer chain, please see
462 http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
463 -->
464
465 <!-- One can also specify an existing Analyzer class that has a
466 default constructor via the class attribute on the analyzer element.
467 Example:
468 <fieldType name="text_greek" class="solr.TextField">
469 <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
470 </fieldType>
471 -->
472
473 <!-- A text field that only splits on whitespace for exact matching of words -->
474 <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
475 <analyzer>
476 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
477 </analyzer>
478 </fieldType>
479
480 <!-- A general text field that has reasonable, generic
481 cross-language defaults: it tokenizes with StandardTokenizer,
482 removes stop words from case-insensitive "stopwords.txt"
483 (empty by default), and down cases. At query time only, it
484 also applies synonyms. -->
485 <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
486 <analyzer type="index">
487 <charFilter class="solr.HTMLStripCharFilterFactory"/>
488 <tokenizer class="solr.StandardTokenizerFactory"/>
489 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
490 <!-- in this example, we will only use synonyms at query time
491 <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
492 -->
493 <filter class="solr.LowerCaseFilterFactory"/>
494 </analyzer>
495 <analyzer type="query">
496 <tokenizer class="solr.StandardTokenizerFactory"/>
497 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
498 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
499 <filter class="solr.LowerCaseFilterFactory"/>
500 </analyzer>
501 </fieldType>
502
503 <!-- A text field with defaults appropriate for English: it
504 tokenizes with StandardTokenizer, removes English stop words
505 (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
506 finally applies Porter's stemming. The query time analyzer
507 also applies synonyms from synonyms.txt. -->
508 <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
509 <analyzer type="index">
510 <charFilter class="solr.HTMLStripCharFilterFactory"/>
511 <tokenizer class="solr.StandardTokenizerFactory"/>
512 <!-- in this example, we will only use synonyms at query time
513 <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
514 -->
515 <!-- Case insensitive stop word removal.
516 -->
517 <filter class="solr.StopFilterFactory"
518 ignoreCase="true"
519 words="lang/stopwords_en.txt"
520 />
521 <filter class="solr.LowerCaseFilterFactory"/>
522 <filter class="solr.EnglishPossessiveFilterFactory"/>
523 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
524 <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
525 <filter class="solr.EnglishMinimalStemFilterFactory"/>
526 -->
527 <!--<filter class="solr.PorterStemFilterFactory"/>-->
528 <filter class="solr.EnglishMinimalStemFilterFactory"/>
529 </analyzer>
530 <analyzer type="query">
531 <tokenizer class="solr.StandardTokenizerFactory"/>
532 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
533 <filter class="solr.StopFilterFactory"
534 ignoreCase="true"
535 words="lang/stopwords_en.txt"
536 />
537 <filter class="solr.LowerCaseFilterFactory"/>
538 <filter class="solr.EnglishPossessiveFilterFactory"/>
539 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
540 <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
541 <filter class="solr.EnglishMinimalStemFilterFactory"/>
542 -->
543 <!--<filter class="solr.PorterStemFilterFactory"/>-->
544 <filter class="solr.EnglishMinimalStemFilterFactory"/>
545 </analyzer>
546 </fieldType>
547
548 <!-- A text field with defaults appropriate for English, plus
549 aggressive word-splitting and autophrase features enabled.
550 This field is just like text_en, except it adds
551 WordDelimiterFilter to enable splitting and matching of
552 words on case-change, alpha numeric boundaries, and
553 non-alphanumeric chars. This means certain compound word
554 cases will work, for example query "wi fi" will match
555 document "WiFi" or "wi-fi".
556 -->
557 <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
558 <analyzer type="index">
559 <charFilter class="solr.HTMLStripCharFilterFactory"/>
560 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
561 <!-- in this example, we will only use synonyms at query time
562 <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
563 -->
564 <!-- Case insensitive stop word removal.
565 -->
566 <filter class="solr.StopFilterFactory"
567 ignoreCase="true"
568 words="lang/stopwords_en.txt"
569 />
570 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
571 <filter class="solr.LowerCaseFilterFactory"/>
572 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
573 <!--<filter class="solr.PorterStemFilterFactory"/>-->
574 <filter class="solr.EnglishMinimalStemFilterFactory"/>
575 </analyzer>
576 <analyzer type="query">
577 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
578 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
579 <filter class="solr.StopFilterFactory"
580 ignoreCase="true"
581 words="lang/stopwords_en.txt"
582 />
583 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
584 <filter class="solr.LowerCaseFilterFactory"/>
585 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
586 <!--<filter class="solr.PorterStemFilterFactory"/>-->
587 <filter class="solr.EnglishMinimalStemFilterFactory"/>
588 </analyzer>
589 </fieldType>
590
591 <!-- Less flexible matching, but less false matches. Probably not ideal for product names,
592 but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
593 <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
594 <analyzer>
595 <charFilter class="solr.HTMLStripCharFilterFactory"/>
596 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
597 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
598 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
599 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
600 <filter class="solr.LowerCaseFilterFactory"/>
601 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
602 <filter class="solr.EnglishMinimalStemFilterFactory"/>
603 <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
604 possible with WordDelimiterFilter in conjuncton with stemming. -->
605 <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
606 </analyzer>
607 </fieldType>
608
609 <!-- Just like text_general except it reverses the characters of
610 each token, to enable more efficient leading wildcard queries. -->
611 <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
612 <analyzer type="index">
613 <tokenizer class="solr.StandardTokenizerFactory"/>
614 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
615 <filter class="solr.LowerCaseFilterFactory"/>
616 <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
617 maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
618 </analyzer>
619 <analyzer type="query">
620 <tokenizer class="solr.StandardTokenizerFactory"/>
621 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
622 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
623 <filter class="solr.LowerCaseFilterFactory"/>
624 </analyzer>
625 </fieldType>
626
627 <!-- charFilter + WhitespaceTokenizer -->
628 <!--
629 <fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
630 <analyzer>
631 <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
632 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
633 </analyzer>
634 </fieldType>
635 -->
636
637 <!-- This is an example of using the KeywordTokenizer along
638 With various TokenFilterFactories to produce a sortable field
639 that does not include some properties of the source text
640 -->
641 <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
642 <analyzer>
643 <!-- KeywordTokenizer does no actual tokenizing, so the entire
644 input string is preserved as a single token
645 -->
646 <tokenizer class="solr.KeywordTokenizerFactory"/>
647 <!-- The LowerCase TokenFilter does what you expect, which can be
648 when you want your sorting to be case insensitive
649 -->
650 <filter class="solr.LowerCaseFilterFactory" />
651 <!-- The TrimFilter removes any leading or trailing whitespace -->
652 <filter class="solr.TrimFilterFactory" />
653 <!-- The PatternReplaceFilter gives you the flexibility to use
654 Java Regular expression to replace any sequence of characters
655 matching a pattern with an arbitrary replacement string,
656 which may include back references to portions of the original
657 string matched by the pattern.
658
659 See the Java Regular Expression documentation for more
660 information on pattern and replacement string syntax.
661
662 http://java.sun.com/j2se/1.6.0/docs/api/java/util/regex/package-summary.html
663 -->
664 <filter class="solr.PatternReplaceFilterFactory"
665 pattern="([^a-z])" replacement="" replace="all"
666 />
667 </analyzer>
668 </fieldType>
669
670 <fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
671 <analyzer>
672 <tokenizer class="solr.StandardTokenizerFactory"/>
673 <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
674 </analyzer>
675 </fieldtype>
676
677 <fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
678 <analyzer>
679 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
680 <!--
681 The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
682 a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
683 Attributes of the DelimitedPayloadTokenFilterFactory :
684 "delimiter" - a one character delimiter. Default is | (pipe)
685 "encoder" - how to encode the following value into a playload
686 float -> org.apache.lucene.analysis.payloads.FloatEncoder,
687 integer -> o.a.l.a.p.IntegerEncoder
688 identity -> o.a.l.a.p.IdentityEncoder
689 Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
690 -->
691 <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
692 </analyzer>
693 </fieldtype>
694
695 <!-- lowercases the entire field value, keeping it as a single token. -->
696 <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
697 <analyzer>
698 <tokenizer class="solr.KeywordTokenizerFactory"/>
699 <filter class="solr.LowerCaseFilterFactory" />
700 </analyzer>
701 </fieldType>
702
703 <!--
704 Example of using PathHierarchyTokenizerFactory at index time, so
705 queries for paths match documents at that path, or in descendent paths
706 -->
707 <fieldType name="descendent_path" class="solr.TextField">
708 <analyzer type="index">
709 <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
710 </analyzer>
711 <analyzer type="query">
712 <tokenizer class="solr.KeywordTokenizerFactory" />
713 </analyzer>
714 </fieldType>
715 <!--
716 Example of using PathHierarchyTokenizerFactory at query time, so
717 queries for paths match documents at that path, or in ancestor paths
718 -->
719 <fieldType name="ancestor_path" class="solr.TextField">
720 <analyzer type="index">
721 <tokenizer class="solr.KeywordTokenizerFactory" />
722 </analyzer>
723 <analyzer type="query">
724 <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
725 </analyzer>
726 </fieldType>
727
728 <!-- since fields of this type are by default not stored or indexed,
729 any data added to them will be ignored outright. -->
730 <fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
731
732 <!-- This point type indexes the coordinates as separate fields (subFields)
733 If subFieldType is defined, it references a type, and a dynamic field
734 definition is created matching *___<typename>. Alternately, if
735 subFieldSuffix is defined, that is used to create the subFields.
736 Example: if subFieldType="double", then the coordinates would be
737 indexed in fields myloc_0___double,myloc_1___double.
738 Example: if subFieldSuffix="_d" then the coordinates would be indexed
739 in fields myloc_0_d,myloc_1_d
740 The subFields are an implementation detail of the fieldType, and end
741 users normally should not need to know about them.
742 -->
743 <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
744
745 <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
746 <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
747
748 <!-- An alternative geospatial field type new to Solr 4. It supports multiValued and polygon shapes.
749 For more information about this and other Spatial fields new to Solr 4, see:
750 http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
751 -->
752 <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
753 geo="true" distErrPct="0.025" maxDistErr="0.000009" units="degrees" />
754
755 <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
756 Parameters:
757 defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
758 precisionStep: Specifies the precisionStep for the TrieLong field used for the amount
759 providerClass: Lets you plug in other exchange provider backend:
760 solr.FileExchangeRateProvider is the default and takes one parameter:
761 currencyConfig: name of an xml file holding exchange rates
762 solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
763 ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
764 refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
765 -->
766 <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
767
768
769
770 <!-- some examples for different languages (generally ordered by ISO code) -->
771
772 <!-- Arabic -->
773 <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
774 <analyzer>
775 <charFilter class="solr.HTMLStripCharFilterFactory"/>
776 <tokenizer class="solr.StandardTokenizerFactory"/>
777 <!-- for any non-arabic -->
778 <filter class="solr.LowerCaseFilterFactory"/>
779 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
780 <!-- normalizes ﻯ to ﻱ, etc -->
781 <filter class="solr.ArabicNormalizationFilterFactory"/>
782 <filter class="solr.ArabicStemFilterFactory"/>
783 </analyzer>
784 </fieldType>
785
786 <!-- Bulgarian -->
787 <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
788 <analyzer>
789 <charFilter class="solr.HTMLStripCharFilterFactory"/>
790 <tokenizer class="solr.StandardTokenizerFactory"/>
791 <filter class="solr.LowerCaseFilterFactory"/>
792 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" />
793 <filter class="solr.BulgarianStemFilterFactory"/>
794 </analyzer>
795 </fieldType>
796
797 <!-- Catalan -->
798 <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
799 <analyzer>
800 <charFilter class="solr.HTMLStripCharFilterFactory"/>
801 <tokenizer class="solr.StandardTokenizerFactory"/>
802 <!-- removes l', etc -->
803 <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
804 <filter class="solr.LowerCaseFilterFactory"/>
805 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" />
806 <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
807 </analyzer>
808 </fieldType>
809
810 <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
811 <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
812 <analyzer>
813 <charFilter class="solr.HTMLStripCharFilterFactory"/>
814 <tokenizer class="solr.StandardTokenizerFactory"/>
815 <!-- normalize width before bigram, as e.g. half-width dakuten combine -->
816 <filter class="solr.CJKWidthFilterFactory"/>
817 <!-- for any non-CJK -->
818 <filter class="solr.LowerCaseFilterFactory"/>
819 <filter class="solr.CJKBigramFilterFactory"/>
820 </analyzer>
821 </fieldType>
822
823 <!-- Kurdish -->
824 <fieldType name="text_ckb" class="solr.TextField" positionIncrementGap="100">
825 <analyzer>
826 <charFilter class="solr.HTMLStripCharFilterFactory"/>
827 <tokenizer class="solr.StandardTokenizerFactory"/>
828 <filter class="solr.SoraniNormalizationFilterFactory"/>
829 <!-- for any latin text -->
830 <filter class="solr.LowerCaseFilterFactory"/>
831 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ckb.txt"/>
832 <filter class="solr.SoraniStemFilterFactory"/>
833 </analyzer>
834 </fieldType>
835
836 <!-- Czech -->
837 <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
838 <analyzer>
839 <charFilter class="solr.HTMLStripCharFilterFactory"/>
840 <tokenizer class="solr.StandardTokenizerFactory"/>
841 <filter class="solr.LowerCaseFilterFactory"/>
842 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" />
843 <filter class="solr.CzechStemFilterFactory"/>
844 </analyzer>
845 </fieldType>
846
847 <!-- Danish -->
848 <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
849 <analyzer>
850 <charFilter class="solr.HTMLStripCharFilterFactory"/>
851 <tokenizer class="solr.StandardTokenizerFactory"/>
852 <filter class="solr.LowerCaseFilterFactory"/>
853 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
854 <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
855 </analyzer>
856 </fieldType>
857
858 <!-- German -->
859 <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
860 <analyzer>
861 <charFilter class="solr.HTMLStripCharFilterFactory"/>
862 <tokenizer class="solr.StandardTokenizerFactory"/>
863 <filter class="solr.LowerCaseFilterFactory"/>
864 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" />
865 <filter class="solr.GermanNormalizationFilterFactory"/>
866 <filter class="solr.GermanLightStemFilterFactory"/>
867 <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
868 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
869 </analyzer>
870 </fieldType>
871
872 <!-- Greek -->
873 <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
874 <analyzer>
875 <charFilter class="solr.HTMLStripCharFilterFactory"/>
876 <tokenizer class="solr.StandardTokenizerFactory"/>
877 <!-- greek specific lowercase for sigma -->
878 <filter class="solr.GreekLowerCaseFilterFactory"/>
879 <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
880 <filter class="solr.GreekStemFilterFactory"/>
881 </analyzer>
882 </fieldType>
883
884 <!-- Spanish -->
885 <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
886 <analyzer>
887 <charFilter class="solr.HTMLStripCharFilterFactory"/>
888 <tokenizer class="solr.StandardTokenizerFactory"/>
889 <filter class="solr.LowerCaseFilterFactory"/>
890 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
891 <filter class="solr.SpanishLightStemFilterFactory"/>
892 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
893 </analyzer>
894 </fieldType>
895
896 <!-- Basque -->
897 <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
898 <analyzer>
899 <charFilter class="solr.HTMLStripCharFilterFactory"/>
900 <tokenizer class="solr.StandardTokenizerFactory"/>
901 <filter class="solr.LowerCaseFilterFactory"/>
902 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" />
903 <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
904 </analyzer>
905 </fieldType>
906
907 <!-- Persian -->
908 <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
909 <analyzer>
910 <!-- for ZWNJ -->
911 <charFilter class="solr.HTMLStripCharFilterFactory"/>
912 <charFilter class="solr.PersianCharFilterFactory"/>
913 <tokenizer class="solr.StandardTokenizerFactory"/>
914 <filter class="solr.LowerCaseFilterFactory"/>
915 <filter class="solr.ArabicNormalizationFilterFactory"/>
916 <filter class="solr.PersianNormalizationFilterFactory"/>
917 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" />
918 </analyzer>
919 </fieldType>
920
921 <!-- Finnish -->
922 <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
923 <analyzer>
924 <charFilter class="solr.HTMLStripCharFilterFactory"/>
925 <tokenizer class="solr.StandardTokenizerFactory"/>
926 <filter class="solr.LowerCaseFilterFactory"/>
927 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
928 <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
929 <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
930 </analyzer>
931 </fieldType>
932
933 <!-- French -->
934 <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
935 <analyzer>
936 <charFilter class="solr.HTMLStripCharFilterFactory"/>
937 <tokenizer class="solr.StandardTokenizerFactory"/>
938 <!-- removes l', etc -->
939 <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
940 <filter class="solr.LowerCaseFilterFactory"/>
941 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
942 <filter class="solr.FrenchLightStemFilterFactory"/>
943 <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
944 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
945 </analyzer>
946 </fieldType>
947
948 <!-- Irish -->
949 <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
950 <analyzer>
951 <charFilter class="solr.HTMLStripCharFilterFactory"/>
952 <tokenizer class="solr.StandardTokenizerFactory"/>
953 <!-- removes d', etc -->
954 <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
955 <!-- removes n-, etc. position increments is intentionally false! -->
956 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
957 <filter class="solr.IrishLowerCaseFilterFactory"/>
958 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/>
959 <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
960 </analyzer>
961 </fieldType>
962
963 <!-- Galician -->
964 <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
965 <analyzer>
966 <charFilter class="solr.HTMLStripCharFilterFactory"/>
967 <tokenizer class="solr.StandardTokenizerFactory"/>
968 <filter class="solr.LowerCaseFilterFactory"/>
969 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" />
970 <filter class="solr.GalicianStemFilterFactory"/>
971 <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
972 </analyzer>
973 </fieldType>
974
975 <!-- Hindi -->
976 <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
977 <analyzer>
978 <charFilter class="solr.HTMLStripCharFilterFactory"/>
979 <tokenizer class="solr.StandardTokenizerFactory"/>
980 <filter class="solr.LowerCaseFilterFactory"/>
981 <!-- normalizes unicode representation -->
982 <filter class="solr.IndicNormalizationFilterFactory"/>
983 <!-- normalizes variation in spelling -->
984 <filter class="solr.HindiNormalizationFilterFactory"/>
985 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
986 <filter class="solr.HindiStemFilterFactory"/>
987 </analyzer>
988 </fieldType>
989
990 <!-- Hungarian -->
991 <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
992 <analyzer>
993 <charFilter class="solr.HTMLStripCharFilterFactory"/>
994 <tokenizer class="solr.StandardTokenizerFactory"/>
995 <filter class="solr.LowerCaseFilterFactory"/>
996 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
997 <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
998 <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
999 </analyzer>
1000 </fieldType>
1001
1002 <!-- Armenian -->
1003 <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
1004 <analyzer>
1005 <charFilter class="solr.HTMLStripCharFilterFactory"/>
1006 <tokenizer class="solr.StandardTokenizerFactory"/>
1007 <filter class="solr.LowerCaseFilterFactory"/>
1008 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" />
1009 <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
1010 </analyzer>
1011 </fieldType>
1012
1013 <!-- Indonesian -->
1014 <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
1015 <analyzer>
1016 <charFilter class="solr.HTMLStripCharFilterFactory"/>
1017 <tokenizer class="solr.StandardTokenizerFactory"/>
1018 <filter class="solr.LowerCaseFilterFactory"/>
1019 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" />
1020 <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
1021 <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
1022 </analyzer>
1023 </fieldType>
1024
1025 <!-- Italian -->
1026 <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
1027 <analyzer>
1028 <charFilter class="solr.HTMLStripCharFilterFactory"/>
1029 <tokenizer class="solr.StandardTokenizerFactory"/>
1030 <!-- removes l', etc -->
1031 <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
1032 <filter class="solr.LowerCaseFilterFactory"/>
1033 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
1034 <filter class="solr.ItalianLightStemFilterFactory"/>
1035 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
1036 </analyzer>
1037 </fieldType>
1038
1039 <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
1040
1041 NOTE: If you want to optimize search for precision, use default operator AND in your query
1042 parser config with <solrQueryParser defaultOperator="AND"/> further down in this file. Use
1043 OR if you would like to optimize for recall (default).
1044 -->
1045 <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
1046 <analyzer>
1047 <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
1048
1049 Kuromoji has a search mode (default) that does segmentation useful for search. A heuristic
1050 is used to segment compounds into its parts and the compound itself is kept as synonym.
1051
1052 Valid values for attribute mode are:
1053 normal: regular segmentation
1054 search: segmentation useful for search with synonyms compounds (default)
1055 extended: same as search mode, but unigrams unknown words (experimental)
1056
1057 For some applications it might be good to use search mode for indexing and normal mode for
1058 queries to reduce recall and prevent parts of compounds from being matched and highlighted.
1059 Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
1060
1061 Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
1062 model with your own entries for segmentation, part-of-speech tags and readings without a need
1063 to specify weights. Notice that user dictionaries have not been subject to extensive testing.
1064
1065 User dictionary attributes are:
1066 userDictionary: user dictionary filename
1067 userDictionaryEncoding: user dictionary encoding (default is UTF-8)
1068
1069 See lang/userdict_ja.txt for a sample user dictionary file.
1070
1071 Punctuation characters are discarded by default. Use discardPunctuation="false" to keep them.
1072
1073 See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
1074 -->
1075 <charFilter class="solr.HTMLStripCharFilterFactory"/>
1076 <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
1077 <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
1078 <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (蟞曞圢) -->
1079 <filter class="solr.JapaneseBaseFormFilterFactory"/>
1080 <!-- Removes tokens with certain part-of-speech tags -->
1081 <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
1082 <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
1083 <filter class="solr.CJKWidthFilterFactory"/>
1084 <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
1085 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" />
1086 <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
1087 <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
1088 <!-- Lower-cases romaji characters -->
1089 <filter class="solr.LowerCaseFilterFactory"/>
1090 </analyzer>
1091 </fieldType>
1092
1093 <!-- Latvian -->
1094 <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
1095 <analyzer>
1096 <charFilter class="solr.HTMLStripCharFilterFactory"/>
1097 <tokenizer class="solr.StandardTokenizerFactory"/>
1098 <filter class="solr.LowerCaseFilterFactory"/>
1099 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" />
1100 <filter class="solr.LatvianStemFilterFactory"/>
1101 </analyzer>
1102 </fieldType>
1103
1104 <!-- Dutch -->
1105 <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
1106 <analyzer>
1107 <charFilter class="solr.HTMLStripCharFilterFactory"/>
1108 <tokenizer class="solr.StandardTokenizerFactory"/>
1109 <filter class="solr.LowerCaseFilterFactory"/>
1110 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
1111 <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
1112 <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
1113 </analyzer>
1114 </fieldType>
1115
1116 <!-- Norwegian -->
1117 <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
1118 <analyzer>
1119 <charFilter class="solr.HTMLStripCharFilterFactory"/>
1120 <tokenizer class="solr.StandardTokenizerFactory"/>
1121 <filter class="solr.LowerCaseFilterFactory"/>
1122 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
1123 <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
1124 <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory" variant="nb"/> -->
1125 <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory" variant="nb"/> -->
1126 <!-- The "light" and "minimal" stemmers support variants: nb=Bokmål, nn=Nynorsk, no=Both -->
1127 </analyzer>
1128 </fieldType>
1129
1130 <!-- Portuguese -->
1131 <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
1132 <analyzer>
1133 <charFilter class="solr.HTMLStripCharFilterFactory"/>
1134 <tokenizer class="solr.StandardTokenizerFactory"/>
1135 <filter class="solr.LowerCaseFilterFactory"/>
1136 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
1137 <filter class="solr.PortugueseLightStemFilterFactory"/>
1138 <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
1139 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
1140 <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
1141 </analyzer>
1142 </fieldType>
1143
1144 <!-- Romanian -->
1145 <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
1146 <analyzer>
1147 <charFilter class="solr.HTMLStripCharFilterFactory"/>
1148 <tokenizer class="solr.StandardTokenizerFactory"/>
1149 <filter class="solr.LowerCaseFilterFactory"/>
1150 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" />
1151 <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
1152 </analyzer>
1153 </fieldType>
1154
1155 <!-- Russian -->
1156 <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
1157 <analyzer>
1158 <charFilter class="solr.HTMLStripCharFilterFactory"/>
1159 <tokenizer class="solr.StandardTokenizerFactory"/>
1160 <filter class="solr.LowerCaseFilterFactory"/>
1161 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
1162 <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
1163 <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
1164 </analyzer>
1165 </fieldType>
1166 <!-- Russian with morphology-->
1167 <fieldType name="text_ru_morph" class="solr.TextField" positionIncrementGap="100">
1168 <analyzer>
1169 <charFilter class="solr.HTMLStripCharFilterFactory"/>
1170 <tokenizer class="solr.StandardTokenizerFactory"/>
1171 <filter class="solr.LowerCaseFilterFactory"/>
1172 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
1173 <filter class="company.evo.jmorphy2.lucene.Jmorphy2StemFilterFactory" dict="lang/pymorphy2_dicts"/>
1174 </analyzer>
1175 </fieldType>
1176
1177 <!-- Swedish -->
1178 <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
1179 <analyzer>
1180 <charFilter class="solr.HTMLStripCharFilterFactory"/>
1181 <tokenizer class="solr.StandardTokenizerFactory"/>
1182 <filter class="solr.LowerCaseFilterFactory"/>
1183 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
1184 <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
1185 <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
1186 </analyzer>
1187 </fieldType>
1188
1189 <!-- Thai -->
1190 <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
1191 <analyzer>
1192 <charFilter class="solr.HTMLStripCharFilterFactory"/>
1193 <tokenizer class="solr.StandardTokenizerFactory"/>
1194 <filter class="solr.LowerCaseFilterFactory"/>
1195 <filter class="solr.ThaiWordFilterFactory"/>
1196 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" />
1197 </analyzer>
1198 </fieldType>
1199
1200 <!-- Turkish -->
1201 <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
1202 <analyzer>
1203 <charFilter class="solr.HTMLStripCharFilterFactory"/>
1204 <tokenizer class="solr.StandardTokenizerFactory"/>
1205 <filter class="solr.TurkishLowerCaseFilterFactory"/>
1206 <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
1207 <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
1208 </analyzer>
1209 </fieldType>
1210
1211 </types>
1212
1213 <!-- Similarity is the scoring routine for each document vs. a query.
1214 A custom Similarity or SimilarityFactory may be specified here, but
1215 the default is fine for most applications.
1216 For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
1217 -->
1218 <!--
1219 <similarity class="com.example.solr.CustomSimilarityFactory">
1220 <str name="paramkey">param value</str>
1221 </similarity>
1222 -->
1223
1224</schema>
Note: See TracBrowser for help on using the repository browser.