1 <?xml version="1.0" encoding="UTF-8" ?>
3 Licensed to the Apache Software Foundation (ASF) under one or more
4 contributor license agreements. See the NOTICE file distributed with
5 this work for additional information regarding copyright ownership.
6 The ASF licenses this file to You under the Apache License, Version 2.0
7 (the "License"); you may not use this file except in compliance with
8 the License. You may obtain a copy of the License at
10 http://www.apache.org/licenses/LICENSE-2.0
12 Unless required by applicable law or agreed to in writing, software
13 distributed under the License is distributed on an "AS IS" BASIS,
14 WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15 See the License for the specific language governing permissions and
16 limitations under the License.
20 This is the Solr schema file. This file should be named "schema.xml" and
21 should be in the conf directory under the solr home
22 (i.e. ./solr/conf/schema.xml by default)
23 or located where the classloader for the Solr webapp can find it.
25 This example schema is the recommended starting point for users.
26 It should be kept correct and concise, usable out-of-the-box.
28 For more information, on how to customize this file, please see
29 http://wiki.apache.org/solr/SchemaXml
31 PERFORMANCE NOTE: this schema includes many optional features and should not
32 be used for benchmarking. To improve performance one could
33 - set stored="false" for all fields possible (esp large fields) when you
34 only need to search on the field but don't need to return the original
36 - set indexed="false" if you don't need to search on the field, but only
37 return the field as a result of searching on other indexed fields.
38 - remove all unneeded copyField statements
39 - for best index size and searching performance, set "index" to false
40 for all general text fields, use copyField to copy them to the
41 catchall "text" field, and use that for searching.
42 - For maximum indexing performance, use the StreamingUpdateSolrServer
44 - Remember to run the JVM in server mode, and use a higher logging level
45 that avoids logging every request
48 <schema name="Local Unified Index" version="1.2">
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="1.2" 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.
59 <!-- field type definitions. The "name" attribute is
60 just a label to be used by field definitions. The "class"
61 attribute and any other attributes determine the real
62 behavior of the fieldType.
63 Class names starting with "solr" refer to java classes in the
64 org.apache.solr.analysis package.
67 <!-- The StrField type is not analyzed, but indexed/stored verbatim.
68 - StrField and TextField support an optional compressThreshold which
69 limits compression (if enabled in the derived fields) to values which
70 exceed a certain size (in characters).
72 <fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
74 <!-- boolean type: "true" or "false" -->
75 <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
76 <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
77 <fieldtype name="binary" class="solr.BinaryField"/>
79 <!-- The optional sortMissingLast and sortMissingFirst attributes are
80 currently supported on types that are sorted internally as strings.
81 This includes "string","boolean","sint","slong","sfloat","sdouble","pdate"
82 - If sortMissingLast="true", then a sort on this field will cause documents
83 without the field to come after documents with the field,
84 regardless of the requested sort order (asc or desc).
85 - If sortMissingFirst="true", then a sort on this field will cause documents
86 without the field to come before documents with the field,
87 regardless of the requested sort order.
88 - If sortMissingLast="false" and sortMissingFirst="false" (the default),
89 then default lucene sorting will be used which places docs without the
90 field first in an ascending sort and last in a descending sort.
94 Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
96 <fieldType name="int" class="solr.TrieIntField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
97 <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
98 <fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
99 <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
102 Numeric field types that index each value at various levels of precision
103 to accelerate range queries when the number of values between the range
104 endpoints is large. See the javadoc for NumericRangeQuery for internal
105 implementation details.
107 Smaller precisionStep values (specified in bits) will lead to more tokens
108 indexed per value, slightly larger index size, and faster range queries.
109 A precisionStep of 0 disables indexing at different precision levels.
111 <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
112 <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
113 <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
114 <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
116 <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
117 is a more restricted form of the canonical representation of dateTime
118 http://www.w3.org/TR/xmlschema-2/#dateTime
119 The trailing "Z" designates UTC time and is mandatory.
120 Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
121 All other components are mandatory.
123 Expressions can also be used to denote calculations that should be
124 performed relative to "NOW" to determine the value, ie...
127 ... Round to the start of the current hour
129 ... Exactly 1 day prior to now
130 NOW/DAY+6MONTHS+3DAYS
131 ... 6 months and 3 days in the future from the start of
134 Consult the DateField javadocs for more information.
136 Note: For faster range queries, consider the tdate type
138 <fieldType name="date" class="solr.TrieDateField" omitNorms="true" precisionStep="0" positionIncrementGap="0"/>
140 <!-- A Trie based date field for faster date range queries and date faceting. -->
141 <fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" precisionStep="6" positionIncrementGap="0"/>
143 <!-- Test of new facet type that would support case-insensitive facetting -->
144 <fieldType name="facet" class="solr.TextField" sortMissingLast="true" omitNorms="true">
146 <!-- KeywordTokenizer does no actual tokenizing, so the entire
147 input string is preserved as a single token
149 <tokenizer class="solr.KeywordTokenizerFactory"/>
150 <!-- The LowerCase TokenFilter does what you expect, which can be
151 when you want your sorting to be case insensitive
153 <filter class="solr.LowerCaseFilterFactory" />
154 <!-- The TrimFilter removes any leading or trailing whitespace -->
155 <filter class="solr.TrimFilterFactory" />
161 These should only be used for compatibility with existing indexes (created with older Solr versions)
162 or if "sortMissingFirst" or "sortMissingLast" functionality is needed. Use Trie based fields instead.
164 Plain numeric field types that store and index the text
165 value verbatim (and hence don't support range queries, since the
166 lexicographic ordering isn't equal to the numeric ordering)
168 <fieldType name="pint" class="solr.IntField" omitNorms="true"/>
169 <fieldType name="plong" class="solr.LongField" omitNorms="true"/>
170 <fieldType name="pfloat" class="solr.FloatField" omitNorms="true"/>
171 <fieldType name="pdouble" class="solr.DoubleField" omitNorms="true"/>
172 <fieldType name="pdate" class="solr.DateField" sortMissingLast="true" omitNorms="true"/>
177 These should only be used for compatibility with existing indexes (created with older Solr versions)
178 or if "sortMissingFirst" or "sortMissingLast" functionality is needed. Use Trie based fields instead.
180 Numeric field types that manipulate the value into
181 a string value that isn't human-readable in its internal form,
182 but with a lexicographic ordering the same as the numeric ordering,
183 so that range queries work correctly.
185 <fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/>
186 <fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/>
187 <fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/>
188 <fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/>
191 <!-- The "RandomSortField" is not used to store or search any
192 data. You can declare fields of this type it in your schema
193 to generate pseudo-random orderings of your docs for sorting
194 purposes. The ordering is generated based on the field name
195 and the version of the index, As long as the index version
196 remains unchanged, and the same field name is reused,
197 the ordering of the docs will be consistent.
198 If you want different psuedo-random orderings of documents,
199 for the same version of the index, use a dynamicField and
202 <fieldType name="random" class="solr.RandomSortField" indexed="true" />
204 <!-- solr.TextField allows the specification of custom text analyzers
205 specified as a tokenizer and a list of token filters. Different
206 analyzers may be specified for indexing and querying.
208 The optional positionIncrementGap puts space between multiple fields of
209 this type on the same document, with the purpose of preventing false phrase
210 matching across fields.
212 For more info on customizing your analyzer chain, please see
213 http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
216 <!-- One can also specify an existing Analyzer class that has a
217 default constructor via the class attribute on the analyzer element
218 <fieldType name="text_greek" class="solr.TextField">
219 <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
223 <!-- A text field that only splits on whitespace for exact matching of words -->
224 <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
226 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
230 <!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
231 words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
232 so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
233 Synonyms and stopwords are customized by external files, and stemming is enabled.
235 <fieldType name="text" class="solr.TextField" positionIncrementGap="100">
236 <analyzer type="index">
237 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
238 <!-- in this example, we will only use synonyms at query time
239 <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
241 <!-- Case insensitive stop word removal.
242 add enablePositionIncrements=true in both the index and query
243 analyzers to leave a 'gap' for more accurate phrase queries.
245 <filter class="solr.StopFilterFactory"
247 words="stopwords.txt"
248 enablePositionIncrements="true"
250 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
251 <filter class="solr.LowerCaseFilterFactory"/>
252 <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
254 <analyzer type="query">
255 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
256 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
257 <filter class="solr.StopFilterFactory"
259 words="stopwords.txt"
260 enablePositionIncrements="true"
262 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
263 <filter class="solr.LowerCaseFilterFactory"/>
264 <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
269 <!-- Less flexible matching, but less false matches. Probably not ideal for product names,
270 but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
271 <fieldType name="textTight" class="solr.TextField" positionIncrementGap="100" >
273 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
274 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
275 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
276 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
277 <filter class="solr.LowerCaseFilterFactory"/>
278 <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
279 <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
280 possible with WordDelimiterFilter in conjuncton with stemming. -->
281 <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
286 <!-- A general unstemmed text field - good if one does not know the language of the field -->
287 <fieldType name="textgen" class="solr.TextField" positionIncrementGap="100">
288 <analyzer type="index">
289 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
290 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
291 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
292 <filter class="solr.LowerCaseFilterFactory"/>
294 <analyzer type="query">
295 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
296 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
297 <filter class="solr.StopFilterFactory"
299 words="stopwords.txt"
300 enablePositionIncrements="true"
302 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
303 <filter class="solr.LowerCaseFilterFactory"/>
308 <!-- A general unstemmed text field that indexes tokens normally and also
309 reversed (via ReversedWildcardFilterFactory), to enable more efficient
310 leading wildcard queries. -->
311 <fieldType name="text_rev" class="solr.TextField" positionIncrementGap="100">
312 <analyzer type="index">
313 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
314 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
315 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
316 <filter class="solr.LowerCaseFilterFactory"/>
317 <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
318 maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
320 <analyzer type="query">
321 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
322 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
323 <filter class="solr.StopFilterFactory"
325 words="stopwords.txt"
326 enablePositionIncrements="true"
328 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
329 <filter class="solr.LowerCaseFilterFactory"/>
333 <!-- charFilter + WhitespaceTokenizer -->
335 <fieldType name="textCharNorm" class="solr.TextField" positionIncrementGap="100" >
337 <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
338 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
343 <!-- This is an example of using the KeywordTokenizer along
344 With various TokenFilterFactories to produce a sortable field
345 that does not include some properties of the source text
347 <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
349 <!-- KeywordTokenizer does no actual tokenizing, so the entire
350 input string is preserved as a single token
352 <tokenizer class="solr.KeywordTokenizerFactory"/>
353 <!-- The LowerCase TokenFilter does what you expect, which can be
354 when you want your sorting to be case insensitive
356 <filter class="solr.LowerCaseFilterFactory" />
357 <!-- The TrimFilter removes any leading or trailing whitespace -->
358 <filter class="solr.TrimFilterFactory" />
359 <!-- The PatternReplaceFilter gives you the flexibility to use
360 Java Regular expression to replace any sequence of characters
361 matching a pattern with an arbitrary replacement string,
362 which may include back references to portions of the original
363 string matched by the pattern.
365 See the Java Regular Expression documentation for more
366 information on pattern and replacement string syntax.
368 http://java.sun.com/j2se/1.5.0/docs/api/java/util/regex/package-summary.html
370 <filter class="solr.PatternReplaceFilterFactory"
371 pattern="([^a-z])" replacement="" replace="all"
376 <fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
378 <tokenizer class="solr.StandardTokenizerFactory"/>
379 <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
383 <fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
385 <tokenizer class="solr.WhitespaceTokenizerFactory"/>
387 The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
388 a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
389 Attributes of the DelimitedPayloadTokenFilterFactory :
390 "delimiter" - a one character delimiter. Default is | (pipe)
391 "encoder" - how to encode the following value into a playload
392 float -> org.apache.lucene.analysis.payloads.FloatEncoder,
393 integer -> o.a.l.a.p.IntegerEncoder
394 identity -> o.a.l.a.p.IdentityEncoder
395 Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
397 <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
401 <!-- lowercases the entire field value, keeping it as a single token. -->
402 <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
404 <tokenizer class="solr.KeywordTokenizerFactory"/>
405 <filter class="solr.LowerCaseFilterFactory" />
410 <!-- since fields of this type are by default not stored or indexed,
411 any data added to them will be ignored outright. -->
412 <fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
415 <fieldType name="subject" class="solr.StrField" positionIncrementGap="100">
418 <tokenizer class="solr.PatternTokenizerFactory" pattern=";" />
419 <filter class="solr.StandardFilterFactory" />
420 <filter class="solr.TrimFilterFactory" />
426 <fieldType name="author" class="solr.TextField" positionIncrementGap="100">
428 <tokenizer class="solr.PatternTokenizerFactory" pattern=";" />
429 <filter class="solr.StandardFilterFactory" />
430 <filter class="solr.TrimFilterFactory" />
432 <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
442 <!-- Valid attributes for fields:
443 name: mandatory - the name for the field
444 type: mandatory - the name of a previously defined type from the
446 indexed: true if this field should be indexed (searchable or sortable)
447 stored: true if this field should be retrievable
448 compressed: [false] if this field should be stored using gzip compression
449 (this will only apply if the field type is compressable; among
450 the standard field types, only TextField and StrField are)
451 multiValued: true if this field may contain multiple values per document
452 omitNorms: (expert) set to true to omit the norms associated with
453 this field (this disables length normalization and index-time
454 boosting for the field, and saves some memory). Only full-text
455 fields or fields that need an index-time boost need norms.
456 termVectors: [false] set to true to store the term vector for a
458 When using MoreLikeThis, fields used for similarity should be
459 stored for best performance.
460 termPositions: Store position information with the term vector.
461 This will increase storage costs.
462 termOffsets: Store offset information with the term vector. This
463 will increase storage costs.
464 default: a value that should be used if no value is specified
465 when adding a document.
470 <field name="id" type="string" indexed="true" stored="true" required="true" />
472 <field name="author" type="text" indexed="true" stored="true" multiValued="true" compressed="false" omitNorms="true"/>
473 <field name="author_exact" type="facet" indexed="true" stored="true" multiValued="true" compressed="false" omitNorms="true"/>
474 <field name="author-date" type="text" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
475 <field name="author-title" type="text" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
477 <field name="corporate-date" type="text" indexed="true" stored="true" omitNorms="true"/>
478 <field name="corporate-location" type="text" indexed="true" stored="true" omitNorms="true"/>
479 <field name="corporate-name" type="text" indexed="true" stored="true" omitNorms="true"/>
481 <field name="callnumber" type="text" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
482 <field name="citation" type="text" indexed="true" stored="true" multiValued="true" compressed="true" omitNorms="true"/>
484 <field name="date" type="text" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
485 <field name="description" type="text_ws" indexed="true" stored="true" multiValued="true" compressed="true" omitNorms="true"/>
487 <field name="edition" type="text" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
489 <field name="electronic-format-instruction" type="text" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
490 <field name="electronic-format-type" type="text" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
491 <field name="electronic-note" type="text" indexed="true" stored="true" multiValued="true" compressed="true" omitNorms="true"/>
492 <field name="electronic-text" type="text" indexed="true" stored="true" multiValued="true" compressed="true" omitNorms="true"/>
493 <field name="electronic-url" type="text" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
495 <field name="isbn" type="text" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
496 <field name="issn" type="text" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
497 <field name="lccn" type="text" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
499 <field name="medium" type="text" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
500 <field name="medium_exact" type="facet" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
502 <field name="meeting-date" type="text" indexed="true" stored="true" omitNorms="true"/>
503 <field name="meeting-location" type="text" indexed="true" stored="true" omitNorms="true"/>
504 <field name="meeting-name" type="text" indexed="true" stored="true" omitNorms="true"/>
506 <field name="series-title" type="text" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
508 <field name="subject" type="text_ws" indexed="true" stored="true" multiValued="true" omitNorms="true" />
509 <field name="subject_exact" type="facet" indexed="true" stored="true" multiValued="true" omitNorms="true" />
510 <field name="subject-long" type="text_ws" indexed="true" stored="true" multiValued="true" omitNorms="true" />
512 <field name="system-control-nr" type="text" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
514 <field name="tech-rep-nr" type="text" indexed="true" multiValued="true" stored="true"/>
516 <field name="title" type="text" indexed="true" multiValued="true" compressed="false" stored="true"/>
517 <field name="title-complete" type="text" indexed="true" multiValued="true" compressed="true" stored="true"/>
518 <field name="title-dates" type="text" indexed="true" multiValued="true" stored="true"/>
519 <field name="title-medium" type="text" indexed="true" multiValued="true" stored="true"/>
520 <field name="title-number-section" type="text" indexed="true" multiValued="true" stored="true"/>
521 <field name="title-remainder" type="text" indexed="true" multiValued="true" stored="true"/>
522 <field name="title-responsibility" type="text" indexed="true" multiValued="true" stored="true"/>
523 <field name="title-uniform" type="text" indexed="true" multiValued="true" stored="true"/>
524 <field name="title-uniform-key" type="text" indexed="true" multiValued="true" stored="true"/>
525 <field name="title-uniform-media" type="text" indexed="true" multiValued="true" stored="true"/>
526 <field name="title-uniform-partname" type="text" indexed="true" multiValued="true" stored="true"/>
527 <field name="title-uniform-parts" type="text" indexed="true" multiValued="true" stored="true"/>
529 <field name="journal-title" type="text" indexed="true" multiValued="true" compressed="false" stored="true"/>
530 <field name="journal-title_exact" type="text" indexed="true" multiValued="true" compressed="false" stored="true"/>
532 <field name="physical-accomp" type="text" indexed="true" stored="true" multiValued="true" />
533 <field name="physical-dimensions" type="text" indexed="true" stored="true" multiValued="true" />
534 <field name="physical-extent" type="text" indexed="true" stored="true" multiValued="true" />
535 <field name="physical-format" type="text" indexed="true" stored="true" multiValued="true" />
536 <field name="physical-specified" type="text" indexed="true" stored="true" multiValued="true" />
537 <field name="physical-unitsize" type="text" indexed="true" stored="true" multiValued="true" />
538 <field name="physical-unittype" type="text" indexed="true" stored="true" multiValued="true" />
540 <field name="publication-date" type="text" indexed="true" stored="true" multiValued="true" />
541 <field name="publication-name" type="text" indexed="true" stored="true" multiValued="true" />
542 <field name="publication-place" type="text" indexed="true" stored="true" multiValued="true" />
545 <!-- Common metadata fields, named specifically to match up with
546 SolrCell metadata when parsing rich documents such as Word, PDF.
547 Some fields are multiValued only because Tika currently may return
548 multiple values for them.
551 <field name="title" type="text" indexed="true" stored="true" multiValued="true"/>
552 <field name="subject" type="text" indexed="true" stored="true"/>
553 <field name="description" type="text" indexed="true" stored="true" multiValued="true"/>
554 <field name="comments" type="text" indexed="true" stored="true"/>
555 <field name="author" type="textgen" indexed="true" stored="true"/>
556 <field name="keywords" type="textgen" indexed="true" stored="true"/>
557 <field name="category" type="textgen" indexed="true" stored="true"/>
558 <field name="content_type" type="string" indexed="true" stored="true" multiValued="true"/>
559 <field name="last_modified" type="date" indexed="true" stored="true"/>
560 <field name="links" type="string" indexed="true" stored="true" multiValued="true"/>
563 <!-- catchall field, containing all other searchable text fields (implemented
564 via copyField further on in this schema -->
565 <field name="text" type="text" indexed="true" stored="false" multiValued="true"/>
567 <!-- catchall text field that indexes tokens both normally and in reverse for efficient
568 leading wildcard queries. -->
569 <field name="text_rev" type="text_rev" indexed="true" stored="false" multiValued="true"/>
571 <field name="payloads" type="payloads" indexed="true" stored="true"/>
573 <!-- Uncommenting the following will create a "timestamp" field using
574 a default value of "NOW" to indicate when each document was indexed.
577 <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
581 <!-- Dynamic field definitions. If a field name is not found, dynamicFields
582 will be used if the name matches any of the patterns.
583 RESTRICTION: the glob-like pattern in the name attribute must have
584 a "*" only at the start or the end.
585 EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
586 Longer patterns will be matched first. if equal size patterns
587 both match, the first appearing in the schema will be used. -->
588 <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
589 <dynamicField name="*_s" type="string" indexed="true" stored="true"/>
590 <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
591 <dynamicField name="*_t" type="text" indexed="true" stored="true"/>
592 <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
593 <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
594 <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
595 <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
597 <!-- some trie-coded dynamic fields for faster range queries -->
598 <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
599 <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
600 <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
601 <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
602 <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
604 <dynamicField name="*_pi" type="pint" indexed="true" stored="true"/>
606 <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
607 <dynamicField name="attr_*" type="textgen" indexed="true" stored="true" multiValued="true"/>
609 <dynamicField name="random_*" type="random" />
611 <!-- uncomment the following to ignore any fields that don't already match an existing
612 field name or dynamic field, rather than reporting them as an error.
613 alternately, change the type="ignored" to some other type e.g. "text" if you want
614 unknown fields indexed and/or stored by default -->
615 <dynamicField name="*" type="text" multiValued="true" />
619 <!-- Field to use to determine and enforce document uniqueness.
620 Unless this field is marked with required="false", it will be a required field
622 <uniqueKey>id</uniqueKey>
624 <!-- field for the QueryParser to use when an explicit fieldname is absent -->
625 <defaultSearchField>text</defaultSearchField>
627 <!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
628 <solrQueryParser defaultOperator="AND"/>
630 <!-- copyField commands copy one field to another at the time a document
631 is added to the index. It's used either to index the same field differently,
632 or to add multiple fields to the same field for easier/faster searching. -->
634 <copyField source="author" dest="author_exact"/>
635 <copyField source="subject" dest="subject_exact"/>
636 <copyField source="medium" dest="medium_exact"/>
637 <copyField source="journal-title" dest="journal-title_exact"/>
639 <!-- Above, multiple source fields are copied to the [text] field.
640 Another way to map multiple source fields to the same
641 destination field is to use the dynamic field syntax.
642 copyField also supports a maxChars to copy setting. -->
644 <copyField source="*" dest="text" maxChars="10000"/>
646 <!-- copy name to alphaNameSort, a field designed for sorting by name -->
647 <!-- <copyField source="name" dest="alphaNameSort"/> -->
650 <!-- Similarity is the scoring routine for each document vs. a query.
651 A custom similarity may be specified here, but the default is fine
652 for most applications. -->
653 <!-- <similarity class="org.apache.lucene.search.DefaultSimilarity"/> -->
655 Specify a SimilarityFactory class name implementation
656 allowing parameters to be used.
659 <similarity class="com.example.solr.CustomSimilarityFactory">
660 <str name="paramkey">param value</str>