source: gs3-extensions/solr/trunk/src/etc/conf/schema.xml@ 24448

Last change on this file since 24448 was 24446, checked in by davidb, 13 years ago

Start of Solr extension for Greenstone3
File size: 33.2 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="1.4">
49 <!-- attribute "name" is the name of this schema and is only used for display purposes.
50 Applications should change this to reflect the nature of the search collection.
51 version="1.4" is Solr's version number for the schema syntax and semantics. It should
52 not normally be changed by applications.
53 1.0: multiValued attribute did not exist, all fields are multiValued by nature
54 1.1: multiValued attribute introduced, false by default
55 1.2: omitTermFreqAndPositions attribute introduced, true by default except for text fields.
56 1.3: removed optional field compress feature
57 1.4: default auto-phrase (QueryParser feature) to off
58 -->
59
60 <types>
61 <!-- field type definitions. The "name" attribute is
62 just a label to be used by field definitions. The "class"
63 attribute and any other attributes determine the real
64 behavior of the fieldType.
65 Class names starting with "solr" refer to java classes in the
66 org.apache.solr.analysis package.
67 -->
68
69 <!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
70 <fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
71
72 <!-- boolean type: "true" or "false" -->
73 <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
74 <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
75 <fieldtype name="binary" class="solr.BinaryField"/>
76
77 <!-- The optional sortMissingLast and sortMissingFirst attributes are
78 currently supported on types that are sorted internally as strings.
79 This includes "string","boolean","sint","slong","sfloat","sdouble","pdate"
80 - If sortMissingLast="true", then a sort on this field will cause documents
81 without the field to come after documents with the field,
82 regardless of the requested sort order (asc or desc).
83 - If sortMissingFirst="true", then a sort on this field will cause documents
84 without the field to come before documents with the field,
85 regardless of the requested sort order.
86 - If sortMissingLast="false" and sortMissingFirst="false" (the default),
87 then default lucene sorting will be used which places docs without the
88 field first in an ascending sort and last in a descending sort.
89 -->
90
91 <!--
92 Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
93 -->
94 <fieldType name="int" class="solr.TrieIntField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
95 <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
96 <fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
97 <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
98
99 <!--
100 Numeric field types that index each value at various levels of precision
101 to accelerate range queries when the number of values between the range
102 endpoints is large. See the javadoc for NumericRangeQuery for internal
103 implementation details.
104
105 Smaller precisionStep values (specified in bits) will lead to more tokens
106 indexed per value, slightly larger index size, and faster range queries.
107 A precisionStep of 0 disables indexing at different precision levels.
108 -->
109 <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
110 <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
111 <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
112 <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
113
114 <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
115 is a more restricted form of the canonical representation of dateTime
116 http://www.w3.org/TR/xmlschema-2/#dateTime
117 The trailing "Z" designates UTC time and is mandatory.
118 Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
119 All other components are mandatory.
120
121 Expressions can also be used to denote calculations that should be
122 performed relative to "NOW" to determine the value, ie...
123
124 NOW/HOUR
125 ... Round to the start of the current hour
126 NOW-1DAY
127 ... Exactly 1 day prior to now
128 NOW/DAY+6MONTHS+3DAYS
129 ... 6 months and 3 days in the future from the start of
130 the current day
131
132 Consult the DateField javadocs for more information.
133
134 Note: For faster range queries, consider the tdate type
135 -->
136 <fieldType name="date" class="solr.TrieDateField" omitNorms="true" precisionStep="0" positionIncrementGap="0"/>
137
138 <!-- A Trie based date field for faster date range queries and date faceting. -->
139 <fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" precisionStep="6" positionIncrementGap="0"/>
140
141
142 <!--
143 Note:
144 These should only be used for compatibility with existing indexes (created with older Solr versions)
145 or if "sortMissingFirst" or "sortMissingLast" functionality is needed. Use Trie based fields instead.
146
147 Plain numeric field types that store and index the text
148 value verbatim (and hence don't support range queries, since the
149 lexicographic ordering isn't equal to the numeric ordering)
150 -->
151 <fieldType name="pint" class="solr.IntField" omitNorms="true"/>
152 <fieldType name="plong" class="solr.LongField" omitNorms="true"/>
153 <fieldType name="pfloat" class="solr.FloatField" omitNorms="true"/>
154 <fieldType name="pdouble" class="solr.DoubleField" omitNorms="true"/>
155 <fieldType name="pdate" class="solr.DateField" sortMissingLast="true" omitNorms="true"/>
156
157
158 <!--
159 Note:
160 These should only be used for compatibility with existing indexes (created with older Solr versions)
161 or if "sortMissingFirst" or "sortMissingLast" functionality is needed. Use Trie based fields instead.
162
163 Numeric field types that manipulate the value into
164 a string value that isn't human-readable in its internal form,
165 but with a lexicographic ordering the same as the numeric ordering,
166 so that range queries work correctly.
167 -->
168 <fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/>
169 <fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/>
170 <fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/>
171 <fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/>
172
173
174 <!-- The "RandomSortField" is not used to store or search any
175 data. You can declare fields of this type it in your schema
176 to generate pseudo-random orderings of your docs for sorting
177 purposes. The ordering is generated based on the field name
178 and the version of the index, As long as the index version
179 remains unchanged, and the same field name is reused,
180 the ordering of the docs will be consistent.
181 If you want different psuedo-random orderings of documents,
182 for the same version of the index, use a dynamicField and
183 change the name
184 -->
185 <fieldType name="random" class="solr.RandomSortField" indexed="true" />
186
187 <!-- solr.TextField allows the specification of custom text analyzers
188 specified as a tokenizer and a list of token filters. Different
189 analyzers may be specified for indexing and querying.
190
191 The optional positionIncrementGap puts space between multiple fields of
192 this type on the same document, with the purpose of preventing false phrase
193 matching across fields.
194
195 For more info on customizing your analyzer chain, please see
196 http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
197 -->
198
199 <!-- One can also specify an existing Analyzer class that has a
200 default constructor via the class attribute on the analyzer element
201 <fieldType name="text_greek" class="solr.TextField">
202 <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
203 </fieldType>
204 -->
205
206 <!-- A text field that only splits on whitespace for exact matching of words -->
207 <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
208 <analyzer>
209 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
210 </analyzer>
211 </fieldType>
212
213 <!-- A general text field that has reasonable, generic
214 cross-language defaults: it tokenizes with StandardTokenizer,
215 removes stop words from case-insensitive "stopwords.txt"
216 (empty by default), and down cases. At query time only, it
217 also applies synonyms. -->
218 <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
219 <analyzer type="index">
220 <tokenizer class="solr.StandardTokenizerFactory"/>
221 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
222 <!-- in this example, we will only use synonyms at query time
223 <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
224 -->
225 <filter class="solr.LowerCaseFilterFactory"/>
226 </analyzer>
227 <analyzer type="query">
228 <tokenizer class="solr.StandardTokenizerFactory"/>
229 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
230 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
231 <filter class="solr.LowerCaseFilterFactory"/>
232 </analyzer>
233 </fieldType>
234
235 <!-- A text field with defaults appropriate for English: it
236 tokenizes with StandardTokenizer, removes English stop words
237 (stopwords_en.txt), down cases, protects words from protwords.txt, and
238 finally applies Porter's stemming. The query time analyzer
239 also applies synonyms from synonyms.txt. -->
240 <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
241 <analyzer type="index">
242 <tokenizer class="solr.StandardTokenizerFactory"/>
243 <!-- in this example, we will only use synonyms at query time
244 <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
245 -->
246 <!-- Case insensitive stop word removal.
247 add enablePositionIncrements=true in both the index and query
248 analyzers to leave a 'gap' for more accurate phrase queries.
249 -->
250 <filter class="solr.StopFilterFactory"
251 ignoreCase="true"
252 words="stopwords_en.txt"
253 enablePositionIncrements="true"
254 />
255 <filter class="solr.LowerCaseFilterFactory"/>
256 <filter class="solr.EnglishPossessiveFilterFactory"/>
257 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
258 <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
259 <filter class="solr.EnglishMinimalStemFilterFactory"/>
260 -->
261 <filter class="solr.PorterStemFilterFactory"/>
262 </analyzer>
263 <analyzer type="query">
264 <tokenizer class="solr.StandardTokenizerFactory"/>
265 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
266 <filter class="solr.StopFilterFactory"
267 ignoreCase="true"
268 words="stopwords_en.txt"
269 enablePositionIncrements="true"
270 />
271 <filter class="solr.LowerCaseFilterFactory"/>
272 <filter class="solr.EnglishPossessiveFilterFactory"/>
273 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
274 <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
275 <filter class="solr.EnglishMinimalStemFilterFactory"/>
276 -->
277 <filter class="solr.PorterStemFilterFactory"/>
278 </analyzer>
279 </fieldType>
280
281 <!-- A text field with defaults appropriate for English, plus
282 aggressive word-splitting and autophrase features enabled.
283 This field is just like text_en, except it adds
284 WordDelimiterFilter to enable splitting and matching of
285 words on case-change, alpha numeric boundaries, and
286 non-alphanumeric chars. This means certain compound word
287 cases will work, for example query "wi fi" will match
288 document "WiFi" or "wi-fi". However, other cases will still
289 not match, for example if the query is "wifi" and the
290 document is "wi fi" or if the query is "wi-fi" and the
291 document is "wifi".
292 -->
293 <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
294 <analyzer type="index">
295 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
296 <!-- in this example, we will only use synonyms at query time
297 <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
298 -->
299 <!-- Case insensitive stop word removal.
300 add enablePositionIncrements=true in both the index and query
301 analyzers to leave a 'gap' for more accurate phrase queries.
302 -->
303 <filter class="solr.StopFilterFactory"
304 ignoreCase="true"
305 words="stopwords_en.txt"
306 enablePositionIncrements="true"
307 />
308 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
309 <filter class="solr.LowerCaseFilterFactory"/>
310 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
311 <filter class="solr.PorterStemFilterFactory"/>
312 </analyzer>
313 <analyzer type="query">
314 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
315 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
316 <filter class="solr.StopFilterFactory"
317 ignoreCase="true"
318 words="stopwords_en.txt"
319 enablePositionIncrements="true"
320 />
321 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
322 <filter class="solr.LowerCaseFilterFactory"/>
323 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
324 <filter class="solr.PorterStemFilterFactory"/>
325 </analyzer>
326 </fieldType>
327
328 <!-- Less flexible matching, but less false matches. Probably not ideal for product names,
329 but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
330 <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
331 <analyzer>
332 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
333 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
334 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_en.txt"/>
335 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
336 <filter class="solr.LowerCaseFilterFactory"/>
337 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
338 <filter class="solr.EnglishMinimalStemFilterFactory"/>
339 <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
340 possible with WordDelimiterFilter in conjuncton with stemming. -->
341 <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
342 </analyzer>
343 </fieldType>
344
345 <!-- Just like text_general except it reverses the characters of
346 each token, to enable more efficient leading wildcard queries. -->
347 <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
348 <analyzer type="index">
349 <tokenizer class="solr.StandardTokenizerFactory"/>
350 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
351 <filter class="solr.LowerCaseFilterFactory"/>
352 <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
353 maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
354 </analyzer>
355 <analyzer type="query">
356 <tokenizer class="solr.StandardTokenizerFactory"/>
357 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
358 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
359 <filter class="solr.LowerCaseFilterFactory"/>
360 </analyzer>
361 </fieldType>
362
363 <!-- charFilter + WhitespaceTokenizer -->
364 <!--
365 <fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
366 <analyzer>
367 <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
368 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
369 </analyzer>
370 </fieldType>
371 -->
372
373 <!-- This is an example of using the KeywordTokenizer along
374 With various TokenFilterFactories to produce a sortable field
375 that does not include some properties of the source text
376 -->
377 <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
378 <analyzer>
379 <!-- KeywordTokenizer does no actual tokenizing, so the entire
380 input string is preserved as a single token
381 -->
382 <tokenizer class="solr.KeywordTokenizerFactory"/>
383 <!-- The LowerCase TokenFilter does what you expect, which can be
384 when you want your sorting to be case insensitive
385 -->
386 <filter class="solr.LowerCaseFilterFactory" />
387 <!-- The TrimFilter removes any leading or trailing whitespace -->
388 <filter class="solr.TrimFilterFactory" />
389 <!-- The PatternReplaceFilter gives you the flexibility to use
390 Java Regular expression to replace any sequence of characters
391 matching a pattern with an arbitrary replacement string,
392 which may include back references to portions of the original
393 string matched by the pattern.
394
395 See the Java Regular Expression documentation for more
396 information on pattern and replacement string syntax.
397
398 http://java.sun.com/j2se/1.5.0/docs/api/java/util/regex/package-summary.html
399 -->
400 <filter class="solr.PatternReplaceFilterFactory"
401 pattern="([^a-z])" replacement="" replace="all"
402 />
403 </analyzer>
404 </fieldType>
405
406 <fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
407 <analyzer>
408 <tokenizer class="solr.StandardTokenizerFactory"/>
409 <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
410 </analyzer>
411 </fieldtype>
412
413 <fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
414 <analyzer>
415 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
416 <!--
417 The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
418 a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
419 Attributes of the DelimitedPayloadTokenFilterFactory :
420 "delimiter" - a one character delimiter. Default is | (pipe)
421 "encoder" - how to encode the following value into a playload
422 float -> org.apache.lucene.analysis.payloads.FloatEncoder,
423 integer -> o.a.l.a.p.IntegerEncoder
424 identity -> o.a.l.a.p.IdentityEncoder
425 Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
426 -->
427 <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
428 </analyzer>
429 </fieldtype>
430
431 <!-- lowercases the entire field value, keeping it as a single token. -->
432 <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
433 <analyzer>
434 <tokenizer class="solr.KeywordTokenizerFactory"/>
435 <filter class="solr.LowerCaseFilterFactory" />
436 </analyzer>
437 </fieldType>
438
439 <fieldType name="text_path" class="solr.TextField" positionIncrementGap="100">
440 <analyzer>
441 <tokenizer class="solr.PathHierarchyTokenizerFactory"/>
442 </analyzer>
443 </fieldType>
444
445 <!-- since fields of this type are by default not stored or indexed,
446 any data added to them will be ignored outright. -->
447 <fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
448
449 <!-- This point type indexes the coordinates as separate fields (subFields)
450 If subFieldType is defined, it references a type, and a dynamic field
451 definition is created matching *___<typename>. Alternately, if
452 subFieldSuffix is defined, that is used to create the subFields.
453 Example: if subFieldType="double", then the coordinates would be
454 indexed in fields myloc_0___double,myloc_1___double.
455 Example: if subFieldSuffix="_d" then the coordinates would be indexed
456 in fields myloc_0_d,myloc_1_d
457 The subFields are an implementation detail of the fieldType, and end
458 users normally should not need to know about them.
459 -->
460 <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
461
462 <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
463 <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
464
465 <!--
466 A Geohash is a compact representation of a latitude longitude pair in a single field.
467 See http://wiki.apache.org/solr/SpatialSearch
468 -->
469 <fieldtype name="geohash" class="solr.GeoHashField"/>
470 </types>
471
472
473 <fields>
474 <!-- Valid attributes for fields:
475 name: mandatory - the name for the field
476 type: mandatory - the name of a previously defined type from the
477 <types> section
478 indexed: true if this field should be indexed (searchable or sortable)
479 stored: true if this field should be retrievable
480 multiValued: true if this field may contain multiple values per document
481 omitNorms: (expert) set to true to omit the norms associated with
482 this field (this disables length normalization and index-time
483 boosting for the field, and saves some memory). Only full-text
484 fields or fields that need an index-time boost need norms.
485 termVectors: [false] set to true to store the term vector for a
486 given field.
487 When using MoreLikeThis, fields used for similarity should be
488 stored for best performance.
489 termPositions: Store position information with the term vector.
490 This will increase storage costs.
491 termOffsets: Store offset information with the term vector. This
492 will increase storage costs.
493 default: a value that should be used if no value is specified
494 when adding a document.
495 -->
496
497 <field name="id" type="string" indexed="true" stored="true" required="true" />
498 <field name="docOID" type="string" indexed="true" stored="true" required="true" />
499 <field name="sku" type="text_en_splitting_tight" indexed="true" stored="true" omitNorms="true"/>
500 <field name="name" type="text_general" indexed="true" stored="true"/>
501 <field name="alphaNameSort" type="alphaOnlySort" indexed="true" stored="false"/>
502 <field name="manu" type="text_general" indexed="true" stored="true" omitNorms="true"/>
503 <field name="cat" type="string" indexed="true" stored="true" multiValued="true"/>
504 <field name="features" type="text_general" indexed="true" stored="true" multiValued="true"/>
505 <field name="includes" type="text_general" indexed="true" stored="true" termVectors="true" termPositions="true" termOffsets="true" />
506
507 <field name="weight" type="float" indexed="true" stored="true"/>
508 <field name="price" type="float" indexed="true" stored="true"/>
509 <field name="popularity" type="int" indexed="true" stored="true" />
510 <field name="inStock" type="boolean" indexed="true" stored="true" />
511
512 <!--
513 The following store examples are used to demonstrate the various ways one might _CHOOSE_ to
514 implement spatial. It is highly unlikely that you would ever have ALL of these fields defined.
515 -->
516 <field name="store" type="location" indexed="true" stored="true"/>
517
518 <!-- Common metadata fields, named specifically to match up with
519 SolrCell metadata when parsing rich documents such as Word, PDF.
520 Some fields are multiValued only because Tika currently may return
521 multiple values for them.
522 -->
523 <field name="title" type="text_general" indexed="true" stored="true" multiValued="true"/>
524 <field name="subject" type="text_general" indexed="true" stored="true"/>
525 <field name="description" type="text_general" indexed="true" stored="true"/>
526 <field name="comments" type="text_general" indexed="true" stored="true"/>
527 <field name="author" type="text_general" indexed="true" stored="true"/>
528 <field name="keywords" type="text_general" indexed="true" stored="true"/>
529 <field name="category" type="text_general" indexed="true" stored="true"/>
530 <field name="content_type" type="string" indexed="true" stored="true" multiValued="true"/>
531 <field name="last_modified" type="date" indexed="true" stored="true"/>
532 <field name="links" type="string" indexed="true" stored="true" multiValued="true"/>
533
534
535 <!-- catchall field, containing all other searchable text fields (implemented
536 via copyField further on in this schema -->
537 <field name="text" type="text_general" indexed="true" stored="false" multiValued="true"/>
538
539 <!-- catchall text field that indexes tokens both normally and in reverse for efficient
540 leading wildcard queries. -->
541 <field name="text_rev" type="text_general_rev" indexed="true" stored="false" multiValued="true"/>
542
543 <!-- non-tokenized version of manufacturer to make it easier to sort or group
544 results by manufacturer. copied from "manu" via copyField -->
545 <field name="manu_exact" type="string" indexed="true" stored="false"/>
546
547 <field name="payloads" type="payloads" indexed="true" stored="true"/>
548
549 <!-- Uncommenting the following will create a "timestamp" field using
550 a default value of "NOW" to indicate when each document was indexed.
551 -->
552 <!--
553 <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
554 -->
555
556
557 <!-- Dynamic field definitions. If a field name is not found, dynamicFields
558 will be used if the name matches any of the patterns.
559 RESTRICTION: the glob-like pattern in the name attribute must have
560 a "*" only at the start or the end.
561 EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
562 Longer patterns will be matched first. if equal size patterns
563 both match, the first appearing in the schema will be used. -->
564 <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
565 <dynamicField name="*_s" type="string" indexed="true" stored="true"/>
566 <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
567 <dynamicField name="*_t" type="text_general" indexed="true" stored="true"/>
568 <dynamicField name="*_txt" type="text_general" indexed="true" stored="true" multiValued="true"/>
569 <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
570 <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
571 <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
572
573 <!-- Type used to index the lat and lon components for the "location" FieldType -->
574 <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false"/>
575
576 <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
577 <dynamicField name="*_p" type="location" indexed="true" stored="true"/>
578
579 <!-- some trie-coded dynamic fields for faster range queries -->
580 <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
581 <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
582 <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
583 <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
584 <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
585
586 <dynamicField name="*_pi" type="pint" indexed="true" stored="true"/>
587
588 <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
589 <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
590
591 <dynamicField name="random_*" type="random" />
592
593 <!-- uncomment the following to ignore any fields that don't already match an existing
594 field name or dynamic field, rather than reporting them as an error.
595 alternately, change the type="ignored" to some other type e.g. "text" if you want
596 unknown fields indexed and/or stored by default -->
597 <!--dynamicField name="*" type="ignored" multiValued="true" /-->
598
599 </fields>
600
601 <!-- Field to use to determine and enforce document uniqueness.
602 Unless this field is marked with required="false", it will be a required field
603 -->
604 <uniqueKey>docOID</uniqueKey>
605
606 <!-- field for the QueryParser to use when an explicit fieldname is absent -->
607 <defaultSearchField>text</defaultSearchField>
608
609 <!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
610 <solrQueryParser defaultOperator="OR"/>
611
612 <!-- copyField commands copy one field to another at the time a document
613 is added to the index. It's used either to index the same field differently,
614 or to add multiple fields to the same field for easier/faster searching. -->
615
616 <copyField source="cat" dest="text"/>
617 <copyField source="name" dest="text"/>
618 <copyField source="manu" dest="text"/>
619 <copyField source="features" dest="text"/>
620 <copyField source="includes" dest="text"/>
621 <copyField source="manu" dest="manu_exact"/>
622
623 <!-- Above, multiple source fields are copied to the [text] field.
624 Another way to map multiple source fields to the same
625 destination field is to use the dynamic field syntax.
626 copyField also supports a maxChars to copy setting. -->
627
628 <!-- <copyField source="*_t" dest="text" maxChars="3000"/> -->
629
630 <!-- copy name to alphaNameSort, a field designed for sorting by name -->
631 <!-- <copyField source="name" dest="alphaNameSort"/> -->
632
633
634 <!-- Similarity is the scoring routine for each document vs. a query.
635 A custom similarity may be specified here, but the default is fine
636 for most applications. -->
637 <!-- <similarity class="org.apache.lucene.search.DefaultSimilarity"/> -->
638 <!-- ... OR ...
639 Specify a SimilarityFactory class name implementation
640 allowing parameters to be used.
641 -->
642 <!--
643 <similarity class="com.example.solr.CustomSimilarityFactory">
644 <str name="paramkey">param value</str>
645 </similarity>
646 -->
647
648
649</schema>
Note: See TracBrowser for help on using the repository browser.