root / solr / conf / schema.xml @ 1206:292dec4eae08
History | View | Annotate | Download (30.5 kB)
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="1.2"> |
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.
|
56 |
-->
|
57 |
|
58 |
<types>
|
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.
|
65 |
-->
|
66 |
|
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).
|
71 |
-->
|
72 |
<fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/> |
73 |
|
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"/> |
78 |
|
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.
|
91 |
-->
|
92 |
|
93 |
<!--
|
94 |
Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
|
95 |
-->
|
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"/> |
100 |
|
101 |
<!--
|
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.
|
106 |
|
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.
|
110 |
-->
|
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"/> |
115 |
|
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.
|
122 |
|
123 |
Expressions can also be used to denote calculations that should be
|
124 |
performed relative to "NOW" to determine the value, ie...
|
125 |
|
126 |
NOW/HOUR
|
127 |
... Round to the start of the current hour
|
128 |
NOW-1DAY
|
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
|
132 |
the current day
|
133 |
|
134 |
Consult the DateField javadocs for more information.
|
135 |
|
136 |
Note: For faster range queries, consider the tdate type
|
137 |
-->
|
138 |
<fieldType name="date" class="solr.TrieDateField" omitNorms="true" precisionStep="0" positionIncrementGap="0"/> |
139 |
|
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"/> |
142 |
|
143 |
|
144 |
<!--
|
145 |
Note:
|
146 |
These should only be used for compatibility with existing indexes (created with older Solr versions)
|
147 |
or if "sortMissingFirst" or "sortMissingLast" functionality is needed. Use Trie based fields instead.
|
148 |
|
149 |
Plain numeric field types that store and index the text
|
150 |
value verbatim (and hence don't support range queries, since the
|
151 |
lexicographic ordering isn't equal to the numeric ordering)
|
152 |
-->
|
153 |
<fieldType name="pint" class="solr.IntField" omitNorms="true"/> |
154 |
<fieldType name="plong" class="solr.LongField" omitNorms="true"/> |
155 |
<fieldType name="pfloat" class="solr.FloatField" omitNorms="true"/> |
156 |
<fieldType name="pdouble" class="solr.DoubleField" omitNorms="true"/> |
157 |
<fieldType name="pdate" class="solr.DateField" sortMissingLast="true" omitNorms="true"/> |
158 |
|
159 |
|
160 |
<!--
|
161 |
Note:
|
162 |
These should only be used for compatibility with existing indexes (created with older Solr versions)
|
163 |
or if "sortMissingFirst" or "sortMissingLast" functionality is needed. Use Trie based fields instead.
|
164 |
|
165 |
Numeric field types that manipulate the value into
|
166 |
a string value that isn't human-readable in its internal form,
|
167 |
but with a lexicographic ordering the same as the numeric ordering,
|
168 |
so that range queries work correctly.
|
169 |
-->
|
170 |
<fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/> |
171 |
<fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/> |
172 |
<fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/> |
173 |
<fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/> |
174 |
|
175 |
|
176 |
<!-- The "RandomSortField" is not used to store or search any
|
177 |
data. You can declare fields of this type it in your schema
|
178 |
to generate pseudo-random orderings of your docs for sorting
|
179 |
purposes. The ordering is generated based on the field name
|
180 |
and the version of the index, As long as the index version
|
181 |
remains unchanged, and the same field name is reused,
|
182 |
the ordering of the docs will be consistent.
|
183 |
If you want different psuedo-random orderings of documents,
|
184 |
for the same version of the index, use a dynamicField and
|
185 |
change the name
|
186 |
-->
|
187 |
<fieldType name="random" class="solr.RandomSortField" indexed="true" /> |
188 |
|
189 |
<!-- solr.TextField allows the specification of custom text analyzers
|
190 |
specified as a tokenizer and a list of token filters. Different
|
191 |
analyzers may be specified for indexing and querying.
|
192 |
|
193 |
The optional positionIncrementGap puts space between multiple fields of
|
194 |
this type on the same document, with the purpose of preventing false phrase
|
195 |
matching across fields.
|
196 |
|
197 |
For more info on customizing your analyzer chain, please see
|
198 |
http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
|
199 |
-->
|
200 |
|
201 |
<!-- One can also specify an existing Analyzer class that has a
|
202 |
default constructor via the class attribute on the analyzer element-->
|
203 |
<fieldType name="text_greek" class="solr.TextField"> |
204 |
<analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/> |
205 |
</fieldType>
|
206 |
|
207 |
<!-- A text field that only splits on whitespace for exact matching of words -->
|
208 |
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100"> |
209 |
<analyzer>
|
210 |
<tokenizer class="solr.WhitespaceTokenizerFactory"/> |
211 |
</analyzer>
|
212 |
</fieldType>
|
213 |
|
214 |
<!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
|
215 |
words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
|
216 |
so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
|
217 |
Synonyms and stopwords are customized by external files, and stemming is enabled.
|
218 |
-->
|
219 |
<fieldType name="text" class="solr.TextField" positionIncrementGap="100"> |
220 |
<analyzer type="index"> |
221 |
<tokenizer class="solr.WhitespaceTokenizerFactory"/> |
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 |
<!-- Case insensitive stop word removal.
|
226 |
add enablePositionIncrements=true in both the index and query
|
227 |
analyzers to leave a 'gap' for more accurate phrase queries.
|
228 |
-->
|
229 |
<filter class="solr.StopFilterFactory" |
230 |
ignoreCase="true" |
231 |
words="stopwords.txt" |
232 |
enablePositionIncrements="true" |
233 |
/>
|
234 |
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="1" splitOnCaseChange="1"/> |
235 |
<filter class="solr.LowerCaseFilterFactory"/> |
236 |
<filter class="org.gss_project.gss.solr.analysis.GreekLowerCaseFilterFactory"/> |
237 |
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/> |
238 |
</analyzer>
|
239 |
<analyzer type="query"> |
240 |
<tokenizer class="solr.WhitespaceTokenizerFactory"/> |
241 |
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> |
242 |
<filter class="solr.StopFilterFactory" |
243 |
ignoreCase="true" |
244 |
words="stopwords.txt" |
245 |
enablePositionIncrements="true" |
246 |
/>
|
247 |
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/> |
248 |
<filter class="solr.LowerCaseFilterFactory"/> |
249 |
<filter class="org.gss_project.gss.solr.analysis.GreekLowerCaseFilterFactory"/> |
250 |
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/> |
251 |
</analyzer>
|
252 |
</fieldType>
|
253 |
|
254 |
|
255 |
<!-- Less flexible matching, but less false matches. Probably not ideal for product names,
|
256 |
but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
|
257 |
<fieldType name="textTight" class="solr.TextField" positionIncrementGap="100" > |
258 |
<analyzer>
|
259 |
<tokenizer class="solr.WhitespaceTokenizerFactory"/> |
260 |
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/> |
261 |
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/> |
262 |
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/> |
263 |
<filter class="solr.LowerCaseFilterFactory"/> |
264 |
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/> |
265 |
<!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
|
266 |
possible with WordDelimiterFilter in conjuncton with stemming. -->
|
267 |
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/> |
268 |
</analyzer>
|
269 |
</fieldType>
|
270 |
|
271 |
|
272 |
<!-- A general unstemmed text field - good if one does not know the language of the field -->
|
273 |
<fieldType name="textgen" class="solr.TextField" positionIncrementGap="100"> |
274 |
<analyzer type="index"> |
275 |
<tokenizer class="solr.WhitespaceTokenizerFactory"/> |
276 |
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" /> |
277 |
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/> |
278 |
<filter class="solr.LowerCaseFilterFactory"/> |
279 |
</analyzer>
|
280 |
<analyzer type="query"> |
281 |
<tokenizer class="solr.WhitespaceTokenizerFactory"/> |
282 |
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> |
283 |
<filter class="solr.StopFilterFactory" |
284 |
ignoreCase="true" |
285 |
words="stopwords.txt" |
286 |
enablePositionIncrements="true" |
287 |
/>
|
288 |
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/> |
289 |
<filter class="solr.LowerCaseFilterFactory"/> |
290 |
</analyzer>
|
291 |
</fieldType>
|
292 |
|
293 |
|
294 |
<!-- A general unstemmed text field that indexes tokens normally and also
|
295 |
reversed (via ReversedWildcardFilterFactory), to enable more efficient
|
296 |
leading wildcard queries. -->
|
297 |
<fieldType name="text_rev" class="solr.TextField" positionIncrementGap="100"> |
298 |
<analyzer type="index"> |
299 |
<tokenizer class="solr.WhitespaceTokenizerFactory"/> |
300 |
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" /> |
301 |
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/> |
302 |
<filter class="solr.LowerCaseFilterFactory"/> |
303 |
<filter class="solr.ReversedWildcardFilterFactory" withOriginal="true" |
304 |
maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/> |
305 |
</analyzer>
|
306 |
<analyzer type="query"> |
307 |
<tokenizer class="solr.WhitespaceTokenizerFactory"/> |
308 |
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> |
309 |
<filter class="solr.StopFilterFactory" |
310 |
ignoreCase="true" |
311 |
words="stopwords.txt" |
312 |
enablePositionIncrements="true" |
313 |
/>
|
314 |
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/> |
315 |
<filter class="solr.LowerCaseFilterFactory"/> |
316 |
</analyzer>
|
317 |
</fieldType>
|
318 |
|
319 |
<!-- charFilter + WhitespaceTokenizer -->
|
320 |
<!--
|
321 |
<fieldType name="textCharNorm" class="solr.TextField" positionIncrementGap="100" >
|
322 |
<analyzer>
|
323 |
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
|
324 |
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
325 |
</analyzer>
|
326 |
</fieldType>
|
327 |
-->
|
328 |
|
329 |
<!-- This is an example of using the KeywordTokenizer along
|
330 |
With various TokenFilterFactories to produce a sortable field
|
331 |
that does not include some properties of the source text
|
332 |
-->
|
333 |
<fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true"> |
334 |
<analyzer>
|
335 |
<!-- KeywordTokenizer does no actual tokenizing, so the entire
|
336 |
input string is preserved as a single token
|
337 |
-->
|
338 |
<tokenizer class="solr.KeywordTokenizerFactory"/> |
339 |
<!-- The LowerCase TokenFilter does what you expect, which can be
|
340 |
when you want your sorting to be case insensitive
|
341 |
-->
|
342 |
<filter class="solr.LowerCaseFilterFactory" /> |
343 |
<!-- The TrimFilter removes any leading or trailing whitespace -->
|
344 |
<filter class="solr.TrimFilterFactory" /> |
345 |
<!-- The PatternReplaceFilter gives you the flexibility to use
|
346 |
Java Regular expression to replace any sequence of characters
|
347 |
matching a pattern with an arbitrary replacement string,
|
348 |
which may include back references to portions of the original
|
349 |
string matched by the pattern.
|
350 |
|
351 |
See the Java Regular Expression documentation for more
|
352 |
information on pattern and replacement string syntax.
|
353 |
|
354 |
http://java.sun.com/j2se/1.5.0/docs/api/java/util/regex/package-summary.html
|
355 |
-->
|
356 |
<filter class="solr.PatternReplaceFilterFactory" |
357 |
pattern="([^a-z])" replacement="" replace="all" |
358 |
/>
|
359 |
</analyzer>
|
360 |
</fieldType>
|
361 |
|
362 |
<fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" > |
363 |
<analyzer>
|
364 |
<tokenizer class="solr.StandardTokenizerFactory"/> |
365 |
<filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/> |
366 |
</analyzer>
|
367 |
</fieldtype>
|
368 |
|
369 |
<fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" > |
370 |
<analyzer>
|
371 |
<tokenizer class="solr.WhitespaceTokenizerFactory"/> |
372 |
<!--
|
373 |
The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
|
374 |
a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
|
375 |
Attributes of the DelimitedPayloadTokenFilterFactory :
|
376 |
"delimiter" - a one character delimiter. Default is | (pipe)
|
377 |
"encoder" - how to encode the following value into a playload
|
378 |
float -> org.apache.lucene.analysis.payloads.FloatEncoder,
|
379 |
integer -> o.a.l.a.p.IntegerEncoder
|
380 |
identity -> o.a.l.a.p.IdentityEncoder
|
381 |
Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
|
382 |
-->
|
383 |
<filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/> |
384 |
</analyzer>
|
385 |
</fieldtype>
|
386 |
|
387 |
<!-- lowercases the entire field value, keeping it as a single token. -->
|
388 |
<fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100"> |
389 |
<analyzer>
|
390 |
<tokenizer class="solr.KeywordTokenizerFactory"/> |
391 |
<filter class="solr.LowerCaseFilterFactory" /> |
392 |
</analyzer>
|
393 |
</fieldType>
|
394 |
|
395 |
|
396 |
<!-- since fields of this type are by default not stored or indexed,
|
397 |
any data added to them will be ignored outright. -->
|
398 |
<fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" /> |
399 |
|
400 |
</types>
|
401 |
|
402 |
|
403 |
<fields>
|
404 |
<!-- Valid attributes for fields:
|
405 |
name: mandatory - the name for the field
|
406 |
type: mandatory - the name of a previously defined type from the
|
407 |
<types> section
|
408 |
indexed: true if this field should be indexed (searchable or sortable)
|
409 |
stored: true if this field should be retrievable
|
410 |
compressed: [false] if this field should be stored using gzip compression
|
411 |
(this will only apply if the field type is compressable; among
|
412 |
the standard field types, only TextField and StrField are)
|
413 |
multiValued: true if this field may contain multiple values per document
|
414 |
omitNorms: (expert) set to true to omit the norms associated with
|
415 |
this field (this disables length normalization and index-time
|
416 |
boosting for the field, and saves some memory). Only full-text
|
417 |
fields or fields that need an index-time boost need norms.
|
418 |
termVectors: [false] set to true to store the term vector for a
|
419 |
given field.
|
420 |
When using MoreLikeThis, fields used for similarity should be
|
421 |
stored for best performance.
|
422 |
termPositions: Store position information with the term vector.
|
423 |
This will increase storage costs.
|
424 |
termOffsets: Store offset information with the term vector. This
|
425 |
will increase storage costs.
|
426 |
default: a value that should be used if no value is specified
|
427 |
when adding a document.
|
428 |
-->
|
429 |
|
430 |
<field name="id" type="string" indexed="true" stored="true" required="true" /> |
431 |
<field name="name" type="text" indexed="true" stored="true" required="true"/> |
432 |
<field name="tag" type="text" indexed="true" stored="true" multiValued="true"/> |
433 |
<field name="owner" type="long" indexed="true" stored="true" required="true"/> |
434 |
<field name="ureaders" type="long" indexed="true" stored="true" multiValued="true"/> |
435 |
<field name="greaders" type="long" indexed="true" stored="true" multiValued="true"/> |
436 |
<field name="public" type="boolean" indexed="true" stored="true" required="true"/> |
437 |
<!-- <field name="sku" type="textTight" indexed="true" stored="true" omitNorms="true"/>
|
438 |
<field name="name" type="textgen" indexed="true" stored="true"/>
|
439 |
<field name="alphaNameSort" type="alphaOnlySort" indexed="true" stored="false"/>
|
440 |
<field name="manu" type="textgen" indexed="true" stored="true" omitNorms="true"/>
|
441 |
<field name="cat" type="text_ws" indexed="true" stored="true" multiValued="true" omitNorms="true" />
|
442 |
<field name="features" type="text" indexed="true" stored="true" multiValued="true"/>
|
443 |
<field name="includes" type="text" indexed="true" stored="true" termVectors="true" termPositions="true" termOffsets="true" />
|
444 |
|
445 |
<field name="weight" type="float" indexed="true" stored="true"/>
|
446 |
<field name="price" type="float" indexed="true" stored="true"/>
|
447 |
<field name="popularity" type="int" indexed="true" stored="true" />
|
448 |
<field name="inStock" type="boolean" indexed="true" stored="true" />-->
|
449 |
|
450 |
|
451 |
<!-- Common metadata fields, named specifically to match up with
|
452 |
SolrCell metadata when parsing rich documents such as Word, PDF.
|
453 |
Some fields are multiValued only because Tika currently may return
|
454 |
multiple values for them.
|
455 |
-->
|
456 |
<!-- <field name="title" type="text" indexed="true" stored="true" multiValued="true"/>
|
457 |
<field name="subject" type="text" indexed="true" stored="true"/>
|
458 |
<field name="description" type="text" indexed="true" stored="true"/>
|
459 |
<field name="comments" type="text" indexed="true" stored="true"/>
|
460 |
<field name="author" type="textgen" indexed="true" stored="true"/>
|
461 |
<field name="keywords" type="textgen" indexed="true" stored="true"/>
|
462 |
<field name="category" type="textgen" indexed="true" stored="true"/>
|
463 |
<field name="content_type" type="string" indexed="true" stored="true" multiValued="true"/>
|
464 |
<field name="last_modified" type="date" indexed="true" stored="true"/>
|
465 |
<field name="links" type="string" indexed="true" stored="true" multiValued="true"/>
|
466 |
-->
|
467 |
|
468 |
<!-- catchall field, containing all other searchable text fields (implemented
|
469 |
via copyField further on in this schema -->
|
470 |
<field name="text" type="text" indexed="true" stored="false" multiValued="true"/> |
471 |
|
472 |
<!-- catchall text field that indexes tokens both normally and in reverse for efficient
|
473 |
leading wildcard queries. -->
|
474 |
<!-- <field name="text_rev" type="text_rev" indexed="true" stored="false" multiValued="true"/>-->
|
475 |
|
476 |
<!-- non-tokenized version of manufacturer to make it easier to sort or group
|
477 |
results by manufacturer. copied from "manu" via copyField -->
|
478 |
<!-- <field name="manu_exact" type="string" indexed="true" stored="false"/>
|
479 |
|
480 |
<field name="payloads" type="payloads" indexed="true" stored="true"/>-->
|
481 |
|
482 |
<!-- Uncommenting the following will create a "timestamp" field using
|
483 |
a default value of "NOW" to indicate when each document was indexed.
|
484 |
-->
|
485 |
<!--
|
486 |
<field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
|
487 |
-->
|
488 |
|
489 |
|
490 |
<!-- Dynamic field definitions. If a field name is not found, dynamicFields
|
491 |
will be used if the name matches any of the patterns.
|
492 |
RESTRICTION: the glob-like pattern in the name attribute must have
|
493 |
a "*" only at the start or the end.
|
494 |
EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
|
495 |
Longer patterns will be matched first. if equal size patterns
|
496 |
both match, the first appearing in the schema will be used. -->
|
497 |
<dynamicField name="*_i" type="int" indexed="true" stored="true"/> |
498 |
<dynamicField name="*_s" type="string" indexed="true" stored="true"/> |
499 |
<dynamicField name="*_l" type="long" indexed="true" stored="true"/> |
500 |
<dynamicField name="*_t" type="text" indexed="true" stored="true"/> |
501 |
<dynamicField name="*_b" type="boolean" indexed="true" stored="true"/> |
502 |
<dynamicField name="*_f" type="float" indexed="true" stored="true"/> |
503 |
<dynamicField name="*_d" type="double" indexed="true" stored="true"/> |
504 |
<dynamicField name="*_dt" type="date" indexed="true" stored="true"/> |
505 |
|
506 |
<!-- some trie-coded dynamic fields for faster range queries -->
|
507 |
<dynamicField name="*_ti" type="tint" indexed="true" stored="true"/> |
508 |
<dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/> |
509 |
<dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/> |
510 |
<dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/> |
511 |
<dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/> |
512 |
|
513 |
<dynamicField name="*_pi" type="pint" indexed="true" stored="true"/> |
514 |
|
515 |
<dynamicField name="ignored_*" type="ignored" multiValued="true"/> |
516 |
<dynamicField name="attr_*" type="textgen" indexed="true" stored="true" multiValued="true"/> |
517 |
|
518 |
<dynamicField name="random_*" type="random" /> |
519 |
|
520 |
<!-- uncomment the following to ignore any fields that don't already match an existing
|
521 |
field name or dynamic field, rather than reporting them as an error.
|
522 |
alternately, change the type="ignored" to some other type e.g. "text" if you want
|
523 |
unknown fields indexed and/or stored by default -->
|
524 |
<!--dynamicField name="*" type="ignored" multiValued="true" /-->
|
525 |
|
526 |
</fields>
|
527 |
|
528 |
<!-- Field to use to determine and enforce document uniqueness.
|
529 |
Unless this field is marked with required="false", it will be a required field
|
530 |
-->
|
531 |
<uniqueKey>id</uniqueKey> |
532 |
|
533 |
<!-- field for the QueryParser to use when an explicit fieldname is absent -->
|
534 |
<defaultSearchField>text</defaultSearchField> |
535 |
|
536 |
<!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
|
537 |
<solrQueryParser defaultOperator="AND"/> |
538 |
|
539 |
<!-- copyField commands copy one field to another at the time a document
|
540 |
is added to the index. It's used either to index the same field differently,
|
541 |
or to add multiple fields to the same field for easier/faster searching. -->
|
542 |
|
543 |
<copyField source="id" dest="text"/> |
544 |
<copyField source="name" dest="text"/> |
545 |
<copyField source="tag" dest="text"/> |
546 |
<!-- <copyField source="cat" dest="text"/>
|
547 |
<copyField source="name" dest="text"/>
|
548 |
<copyField source="manu" dest="text"/>
|
549 |
<copyField source="features" dest="text"/>
|
550 |
<copyField source="includes" dest="text"/>
|
551 |
<copyField source="manu" dest="manu_exact"/>-->
|
552 |
|
553 |
<!-- Above, multiple source fields are copied to the [text] field.
|
554 |
Another way to map multiple source fields to the same
|
555 |
destination field is to use the dynamic field syntax.
|
556 |
copyField also supports a maxChars to copy setting. -->
|
557 |
|
558 |
<!-- <copyField source="*_t" dest="text" maxChars="3000"/> -->
|
559 |
|
560 |
<!-- copy name to alphaNameSort, a field designed for sorting by name -->
|
561 |
<!-- <copyField source="name" dest="alphaNameSort"/> -->
|
562 |
|
563 |
|
564 |
<!-- Similarity is the scoring routine for each document vs. a query.
|
565 |
A custom similarity may be specified here, but the default is fine
|
566 |
for most applications. -->
|
567 |
<!-- <similarity class="org.apache.lucene.search.DefaultSimilarity"/> -->
|
568 |
<!-- ... OR ...
|
569 |
Specify a SimilarityFactory class name implementation
|
570 |
allowing parameters to be used.
|
571 |
-->
|
572 |
<!--
|
573 |
<similarity class="com.example.solr.CustomSimilarityFactory">
|
574 |
<str name="paramkey">param value</str>
|
575 |
</similarity>
|
576 |
-->
|
577 |
|
578 |
|
579 |
</schema>
|