solr_ead 0.4.5 → 0.5.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +15 -0
- data/.gitignore +2 -0
- data/.travis.yml +7 -0
- data/README.md +61 -43
- data/Rakefile +2 -1
- data/config/jetty.yml +9 -0
- data/config/solr.yml +3 -3
- data/lib/solr_ead/behaviors.rb +8 -8
- data/lib/solr_ead/component.rb +16 -4
- data/lib/solr_ead/document.rb +10 -7
- data/lib/solr_ead/indexer.rb +35 -31
- data/lib/solr_ead/version.rb +1 -1
- data/lib/solr_ead.rb +16 -14
- data/lib/tasks/solr_ead_dev.rake +22 -0
- data/solr/schema.xml +1163 -0
- data/solr_ead.gemspec +9 -7
- data/spec/component_spec.rb +18 -18
- data/spec/document_spec.rb +12 -14
- data/spec/indexer_spec.rb +8 -8
- metadata +31 -42
- data/Gemfile.lock +0 -80
- data/lib/ead_mapper.rb +0 -13
data/solr/schema.xml
ADDED
@@ -0,0 +1,1163 @@
|
|
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
|
+
<schema name="Rock and Roll Hall of Fame - Catalog Solr Schema" version="1.5">
|
20
|
+
|
21
|
+
<types>
|
22
|
+
<!-- field type definitions. The "name" attribute is
|
23
|
+
just a label to be used by field definitions. The "class"
|
24
|
+
attribute and any other attributes determine the real
|
25
|
+
behavior of the fieldType.
|
26
|
+
Class names starting with "solr" refer to java classes in a
|
27
|
+
standard package such as org.apache.solr.analysis
|
28
|
+
-->
|
29
|
+
|
30
|
+
<!-- The StrField type is not analyzed, but indexed/stored verbatim.
|
31
|
+
It supports doc values but in that case the field needs to be
|
32
|
+
single-valued and either required or have a default value.
|
33
|
+
-->
|
34
|
+
<fieldType name="string" class="solr.StrField" sortMissingLast="true" />
|
35
|
+
|
36
|
+
<!-- boolean type: "true" or "false" -->
|
37
|
+
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
|
38
|
+
|
39
|
+
<!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
|
40
|
+
currently supported on types that are sorted internally as strings
|
41
|
+
and on numeric types.
|
42
|
+
This includes "string","boolean", and, as of 3.5 (and 4.x),
|
43
|
+
int, float, long, date, double, including the "Trie" variants.
|
44
|
+
- If sortMissingLast="true", then a sort on this field will cause documents
|
45
|
+
without the field to come after documents with the field,
|
46
|
+
regardless of the requested sort order (asc or desc).
|
47
|
+
- If sortMissingFirst="true", then a sort on this field will cause documents
|
48
|
+
without the field to come before documents with the field,
|
49
|
+
regardless of the requested sort order.
|
50
|
+
- If sortMissingLast="false" and sortMissingFirst="false" (the default),
|
51
|
+
then default lucene sorting will be used which places docs without the
|
52
|
+
field first in an ascending sort and last in a descending sort.
|
53
|
+
-->
|
54
|
+
|
55
|
+
<!--
|
56
|
+
Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
|
57
|
+
|
58
|
+
These fields support doc values, but they require the field to be
|
59
|
+
single-valued and either be required or have a default value.
|
60
|
+
-->
|
61
|
+
<fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
|
62
|
+
<fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
|
63
|
+
<fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
|
64
|
+
<fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
|
65
|
+
|
66
|
+
<!--
|
67
|
+
Numeric field types that index each value at various levels of precision
|
68
|
+
to accelerate range queries when the number of values between the range
|
69
|
+
endpoints is large. See the javadoc for NumericRangeQuery for internal
|
70
|
+
implementation details.
|
71
|
+
|
72
|
+
Smaller precisionStep values (specified in bits) will lead to more tokens
|
73
|
+
indexed per value, slightly larger index size, and faster range queries.
|
74
|
+
A precisionStep of 0 disables indexing at different precision levels.
|
75
|
+
-->
|
76
|
+
<fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
|
77
|
+
<fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
|
78
|
+
<fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
|
79
|
+
<fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
|
80
|
+
|
81
|
+
<!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
|
82
|
+
is a more restricted form of the canonical representation of dateTime
|
83
|
+
http://www.w3.org/TR/xmlschema-2/#dateTime
|
84
|
+
The trailing "Z" designates UTC time and is mandatory.
|
85
|
+
Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
|
86
|
+
All other components are mandatory.
|
87
|
+
|
88
|
+
Expressions can also be used to denote calculations that should be
|
89
|
+
performed relative to "NOW" to determine the value, ie...
|
90
|
+
|
91
|
+
NOW/HOUR
|
92
|
+
... Round to the start of the current hour
|
93
|
+
NOW-1DAY
|
94
|
+
... Exactly 1 day prior to now
|
95
|
+
NOW/DAY+6MONTHS+3DAYS
|
96
|
+
... 6 months and 3 days in the future from the start of
|
97
|
+
the current day
|
98
|
+
|
99
|
+
Consult the DateField javadocs for more information.
|
100
|
+
|
101
|
+
Note: For faster range queries, consider the tdate type
|
102
|
+
-->
|
103
|
+
<fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
|
104
|
+
|
105
|
+
<!-- A Trie based date field for faster date range queries and date faceting. -->
|
106
|
+
<fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
|
107
|
+
|
108
|
+
|
109
|
+
<!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
|
110
|
+
<fieldtype name="binary" class="solr.BinaryField"/>
|
111
|
+
|
112
|
+
<!--
|
113
|
+
Note:
|
114
|
+
These should only be used for compatibility with existing indexes (created with lucene or older Solr versions).
|
115
|
+
Use Trie based fields instead. As of Solr 3.5 and 4.x, Trie based fields support sortMissingFirst/Last
|
116
|
+
|
117
|
+
Plain numeric field types that store and index the text
|
118
|
+
value verbatim (and hence don't correctly support range queries, since the
|
119
|
+
lexicographic ordering isn't equal to the numeric ordering)
|
120
|
+
-->
|
121
|
+
<fieldType name="pint" class="solr.IntField"/>
|
122
|
+
<fieldType name="plong" class="solr.LongField"/>
|
123
|
+
<fieldType name="pfloat" class="solr.FloatField"/>
|
124
|
+
<fieldType name="pdouble" class="solr.DoubleField"/>
|
125
|
+
<fieldType name="pdate" class="solr.DateField" sortMissingLast="true"/>
|
126
|
+
|
127
|
+
<!-- The "RandomSortField" is not used to store or search any
|
128
|
+
data. You can declare fields of this type it in your schema
|
129
|
+
to generate pseudo-random orderings of your docs for sorting
|
130
|
+
or function purposes. The ordering is generated based on the field
|
131
|
+
name and the version of the index. As long as the index version
|
132
|
+
remains unchanged, and the same field name is reused,
|
133
|
+
the ordering of the docs will be consistent.
|
134
|
+
If you want different psuedo-random orderings of documents,
|
135
|
+
for the same version of the index, use a dynamicField and
|
136
|
+
change the field name in the request.
|
137
|
+
-->
|
138
|
+
<fieldType name="random" class="solr.RandomSortField" indexed="true" />
|
139
|
+
|
140
|
+
<!-- solr.TextField allows the specification of custom text analyzers
|
141
|
+
specified as a tokenizer and a list of token filters. Different
|
142
|
+
analyzers may be specified for indexing and querying.
|
143
|
+
|
144
|
+
The optional positionIncrementGap puts space between multiple fields of
|
145
|
+
this type on the same document, with the purpose of preventing false phrase
|
146
|
+
matching across fields.
|
147
|
+
|
148
|
+
For more info on customizing your analyzer chain, please see
|
149
|
+
http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
|
150
|
+
-->
|
151
|
+
|
152
|
+
<!-- One can also specify an existing Analyzer class that has a
|
153
|
+
default constructor via the class attribute on the analyzer element.
|
154
|
+
Example:
|
155
|
+
<fieldType name="text_greek" class="solr.TextField">
|
156
|
+
<analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
|
157
|
+
</fieldType>
|
158
|
+
-->
|
159
|
+
|
160
|
+
<!-- A text field that only splits on whitespace for exact matching of words -->
|
161
|
+
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
|
162
|
+
<analyzer>
|
163
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
164
|
+
</analyzer>
|
165
|
+
</fieldType>
|
166
|
+
|
167
|
+
<!-- A general text field that has reasonable, generic
|
168
|
+
cross-language defaults: it tokenizes with StandardTokenizer,
|
169
|
+
removes stop words from case-insensitive "stopwords.txt"
|
170
|
+
(empty by default), and down cases. At query time only, it
|
171
|
+
also applies synonyms. -->
|
172
|
+
<fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
|
173
|
+
<analyzer type="index">
|
174
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
175
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
|
176
|
+
<!-- in this example, we will only use synonyms at query time
|
177
|
+
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
|
178
|
+
-->
|
179
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
180
|
+
</analyzer>
|
181
|
+
<analyzer type="query">
|
182
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
183
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
|
184
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
185
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
186
|
+
</analyzer>
|
187
|
+
</fieldType>
|
188
|
+
|
189
|
+
<!-- Carry-over from solr 4.1 schema. Could be removed and a similar or equal type used instead -->
|
190
|
+
<fieldType name="textSpell" class="solr.TextField" positionIncrementGap="100" >
|
191
|
+
<analyzer>
|
192
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
193
|
+
<!-- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/> -->
|
194
|
+
<filter class="solr.StandardFilterFactory"/>
|
195
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
196
|
+
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
197
|
+
</analyzer>
|
198
|
+
</fieldType>
|
199
|
+
|
200
|
+
<!-- A text field with defaults appropriate for English: it
|
201
|
+
tokenizes with StandardTokenizer, removes English stop words
|
202
|
+
(lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
|
203
|
+
finally applies Porter's stemming. The query time analyzer
|
204
|
+
also applies synonyms from synonyms.txt. -->
|
205
|
+
<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
|
206
|
+
<analyzer type="index">
|
207
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
208
|
+
<!-- in this example, we will only use synonyms at query time
|
209
|
+
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
|
210
|
+
-->
|
211
|
+
<!-- Case insensitive stop word removal.
|
212
|
+
add enablePositionIncrements=true in both the index and query
|
213
|
+
analyzers to leave a 'gap' for more accurate phrase queries.
|
214
|
+
-->
|
215
|
+
<filter class="solr.StopFilterFactory"
|
216
|
+
ignoreCase="true"
|
217
|
+
words="lang/stopwords_en.txt"
|
218
|
+
enablePositionIncrements="true"
|
219
|
+
/>
|
220
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
221
|
+
<filter class="solr.EnglishPossessiveFilterFactory"/>
|
222
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
223
|
+
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
|
224
|
+
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
225
|
+
-->
|
226
|
+
<filter class="solr.PorterStemFilterFactory"/>
|
227
|
+
</analyzer>
|
228
|
+
<analyzer type="query">
|
229
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
230
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
231
|
+
<filter class="solr.StopFilterFactory"
|
232
|
+
ignoreCase="true"
|
233
|
+
words="lang/stopwords_en.txt"
|
234
|
+
enablePositionIncrements="true"
|
235
|
+
/>
|
236
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
237
|
+
<filter class="solr.EnglishPossessiveFilterFactory"/>
|
238
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
239
|
+
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
|
240
|
+
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
241
|
+
-->
|
242
|
+
<filter class="solr.PorterStemFilterFactory"/>
|
243
|
+
</analyzer>
|
244
|
+
</fieldType>
|
245
|
+
|
246
|
+
<!-- A text field with defaults appropriate for English, plus
|
247
|
+
aggressive word-splitting and autophrase features enabled.
|
248
|
+
This field is just like text_en, except it adds
|
249
|
+
WordDelimiterFilter to enable splitting and matching of
|
250
|
+
words on case-change, alpha numeric boundaries, and
|
251
|
+
non-alphanumeric chars. This means certain compound word
|
252
|
+
cases will work, for example query "wi fi" will match
|
253
|
+
document "WiFi" or "wi-fi".
|
254
|
+
-->
|
255
|
+
<fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
|
256
|
+
<analyzer type="index">
|
257
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
258
|
+
<!-- in this example, we will only use synonyms at query time
|
259
|
+
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
|
260
|
+
-->
|
261
|
+
<!-- Case insensitive stop word removal.
|
262
|
+
add enablePositionIncrements=true in both the index and query
|
263
|
+
analyzers to leave a 'gap' for more accurate phrase queries.
|
264
|
+
-->
|
265
|
+
<filter class="solr.StopFilterFactory"
|
266
|
+
ignoreCase="true"
|
267
|
+
words="lang/stopwords_en.txt"
|
268
|
+
enablePositionIncrements="true"
|
269
|
+
/>
|
270
|
+
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
|
271
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
272
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
273
|
+
<filter class="solr.PorterStemFilterFactory"/>
|
274
|
+
</analyzer>
|
275
|
+
<analyzer type="query">
|
276
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
277
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
278
|
+
<filter class="solr.StopFilterFactory"
|
279
|
+
ignoreCase="true"
|
280
|
+
words="lang/stopwords_en.txt"
|
281
|
+
enablePositionIncrements="true"
|
282
|
+
/>
|
283
|
+
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
|
284
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
285
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
286
|
+
<filter class="solr.PorterStemFilterFactory"/>
|
287
|
+
</analyzer>
|
288
|
+
</fieldType>
|
289
|
+
|
290
|
+
<!-- Less flexible matching, but less false matches. Probably not ideal for product names,
|
291
|
+
but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
|
292
|
+
<fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
|
293
|
+
<analyzer>
|
294
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
295
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
|
296
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
|
297
|
+
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
|
298
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
299
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
300
|
+
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
301
|
+
<!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
|
302
|
+
possible with WordDelimiterFilter in conjuncton with stemming. -->
|
303
|
+
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
304
|
+
</analyzer>
|
305
|
+
</fieldType>
|
306
|
+
|
307
|
+
<!-- Just like text_general except it reverses the characters of
|
308
|
+
each token, to enable more efficient leading wildcard queries. -->
|
309
|
+
<fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
|
310
|
+
<analyzer type="index">
|
311
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
312
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
|
313
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
314
|
+
<filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
|
315
|
+
maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
|
316
|
+
</analyzer>
|
317
|
+
<analyzer type="query">
|
318
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
319
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
320
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
|
321
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
322
|
+
</analyzer>
|
323
|
+
</fieldType>
|
324
|
+
|
325
|
+
<!-- charFilter + WhitespaceTokenizer -->
|
326
|
+
<!--
|
327
|
+
<fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
|
328
|
+
<analyzer>
|
329
|
+
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
|
330
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
331
|
+
</analyzer>
|
332
|
+
</fieldType>
|
333
|
+
-->
|
334
|
+
|
335
|
+
<!-- This is an example of using the KeywordTokenizer along
|
336
|
+
With various TokenFilterFactories to produce a sortable field
|
337
|
+
that does not include some properties of the source text
|
338
|
+
-->
|
339
|
+
<fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
|
340
|
+
<analyzer>
|
341
|
+
<!-- KeywordTokenizer does no actual tokenizing, so the entire
|
342
|
+
input string is preserved as a single token
|
343
|
+
-->
|
344
|
+
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
345
|
+
<!-- The LowerCase TokenFilter does what you expect, which can be
|
346
|
+
when you want your sorting to be case insensitive
|
347
|
+
-->
|
348
|
+
<filter class="solr.LowerCaseFilterFactory" />
|
349
|
+
<!-- The TrimFilter removes any leading or trailing whitespace -->
|
350
|
+
<filter class="solr.TrimFilterFactory" />
|
351
|
+
<!-- The PatternReplaceFilter gives you the flexibility to use
|
352
|
+
Java Regular expression to replace any sequence of characters
|
353
|
+
matching a pattern with an arbitrary replacement string,
|
354
|
+
which may include back references to portions of the original
|
355
|
+
string matched by the pattern.
|
356
|
+
|
357
|
+
See the Java Regular Expression documentation for more
|
358
|
+
information on pattern and replacement string syntax.
|
359
|
+
|
360
|
+
http://java.sun.com/j2se/1.6.0/docs/api/java/util/regex/package-summary.html
|
361
|
+
-->
|
362
|
+
<filter class="solr.PatternReplaceFilterFactory"
|
363
|
+
pattern="([^a-z])" replacement="" replace="all"
|
364
|
+
/>
|
365
|
+
</analyzer>
|
366
|
+
</fieldType>
|
367
|
+
|
368
|
+
<fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
|
369
|
+
<analyzer>
|
370
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
371
|
+
<filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
|
372
|
+
</analyzer>
|
373
|
+
</fieldtype>
|
374
|
+
|
375
|
+
<fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
|
376
|
+
<analyzer>
|
377
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
378
|
+
<!--
|
379
|
+
The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
|
380
|
+
a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
|
381
|
+
Attributes of the DelimitedPayloadTokenFilterFactory :
|
382
|
+
"delimiter" - a one character delimiter. Default is | (pipe)
|
383
|
+
"encoder" - how to encode the following value into a playload
|
384
|
+
float -> org.apache.lucene.analysis.payloads.FloatEncoder,
|
385
|
+
integer -> o.a.l.a.p.IntegerEncoder
|
386
|
+
identity -> o.a.l.a.p.IdentityEncoder
|
387
|
+
Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
|
388
|
+
-->
|
389
|
+
<filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
|
390
|
+
</analyzer>
|
391
|
+
</fieldtype>
|
392
|
+
|
393
|
+
<!-- lowercases the entire field value, keeping it as a single token. -->
|
394
|
+
<fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
|
395
|
+
<analyzer>
|
396
|
+
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
397
|
+
<filter class="solr.LowerCaseFilterFactory" />
|
398
|
+
</analyzer>
|
399
|
+
</fieldType>
|
400
|
+
|
401
|
+
<!--
|
402
|
+
Example of using PathHierarchyTokenizerFactory at index time, so
|
403
|
+
queries for paths match documents at that path, or in descendent paths
|
404
|
+
-->
|
405
|
+
<fieldType name="descendent_path" class="solr.TextField">
|
406
|
+
<analyzer type="index">
|
407
|
+
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
|
408
|
+
</analyzer>
|
409
|
+
<analyzer type="query">
|
410
|
+
<tokenizer class="solr.KeywordTokenizerFactory" />
|
411
|
+
</analyzer>
|
412
|
+
</fieldType>
|
413
|
+
<!--
|
414
|
+
Example of using PathHierarchyTokenizerFactory at query time, so
|
415
|
+
queries for paths match documents at that path, or in ancestor paths
|
416
|
+
-->
|
417
|
+
<fieldType name="ancestor_path" class="solr.TextField">
|
418
|
+
<analyzer type="index">
|
419
|
+
<tokenizer class="solr.KeywordTokenizerFactory" />
|
420
|
+
</analyzer>
|
421
|
+
<analyzer type="query">
|
422
|
+
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
|
423
|
+
</analyzer>
|
424
|
+
</fieldType>
|
425
|
+
|
426
|
+
<!-- since fields of this type are by default not stored or indexed,
|
427
|
+
any data added to them will be ignored outright. -->
|
428
|
+
<fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
|
429
|
+
|
430
|
+
<!-- This point type indexes the coordinates as separate fields (subFields)
|
431
|
+
If subFieldType is defined, it references a type, and a dynamic field
|
432
|
+
definition is created matching *___<typename>. Alternately, if
|
433
|
+
subFieldSuffix is defined, that is used to create the subFields.
|
434
|
+
Example: if subFieldType="double", then the coordinates would be
|
435
|
+
indexed in fields myloc_0___double,myloc_1___double.
|
436
|
+
Example: if subFieldSuffix="_d" then the coordinates would be indexed
|
437
|
+
in fields myloc_0_d,myloc_1_d
|
438
|
+
The subFields are an implementation detail of the fieldType, and end
|
439
|
+
users normally should not need to know about them.
|
440
|
+
-->
|
441
|
+
<fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
|
442
|
+
|
443
|
+
<!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
|
444
|
+
<fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
|
445
|
+
|
446
|
+
<!-- An alternative geospatial field type new to Solr 4. It supports multiValued and polygon shapes.
|
447
|
+
For more information about this and other Spatial fields new to Solr 4, see:
|
448
|
+
http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
|
449
|
+
-->
|
450
|
+
<fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
|
451
|
+
geo="true" distErrPct="0.025" maxDistErr="0.000009" units="degrees" />
|
452
|
+
|
453
|
+
<!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
|
454
|
+
Parameters:
|
455
|
+
defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
|
456
|
+
precisionStep: Specifies the precisionStep for the TrieLong field used for the amount
|
457
|
+
providerClass: Lets you plug in other exchange provider backend:
|
458
|
+
solr.FileExchangeRateProvider is the default and takes one parameter:
|
459
|
+
currencyConfig: name of an xml file holding exchange rates
|
460
|
+
solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
|
461
|
+
ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
|
462
|
+
refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
|
463
|
+
-->
|
464
|
+
<fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
|
465
|
+
|
466
|
+
|
467
|
+
|
468
|
+
<!-- some examples for different languages (generally ordered by ISO code) -->
|
469
|
+
|
470
|
+
<!-- Arabic -->
|
471
|
+
<fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
|
472
|
+
<analyzer>
|
473
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
474
|
+
<!-- for any non-arabic -->
|
475
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
476
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" enablePositionIncrements="true"/>
|
477
|
+
<!-- normalizes ﻯ to ﻱ, etc -->
|
478
|
+
<filter class="solr.ArabicNormalizationFilterFactory"/>
|
479
|
+
<filter class="solr.ArabicStemFilterFactory"/>
|
480
|
+
</analyzer>
|
481
|
+
</fieldType>
|
482
|
+
|
483
|
+
<!-- Bulgarian -->
|
484
|
+
<fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
|
485
|
+
<analyzer>
|
486
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
487
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
488
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" enablePositionIncrements="true"/>
|
489
|
+
<filter class="solr.BulgarianStemFilterFactory"/>
|
490
|
+
</analyzer>
|
491
|
+
</fieldType>
|
492
|
+
|
493
|
+
<!-- Catalan -->
|
494
|
+
<fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
|
495
|
+
<analyzer>
|
496
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
497
|
+
<!-- removes l', etc -->
|
498
|
+
<filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
|
499
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
500
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" enablePositionIncrements="true"/>
|
501
|
+
<filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
|
502
|
+
</analyzer>
|
503
|
+
</fieldType>
|
504
|
+
|
505
|
+
<!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
|
506
|
+
<fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
|
507
|
+
<analyzer>
|
508
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
509
|
+
<!-- normalize width before bigram, as e.g. half-width dakuten combine -->
|
510
|
+
<filter class="solr.CJKWidthFilterFactory"/>
|
511
|
+
<!-- for any non-CJK -->
|
512
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
513
|
+
<filter class="solr.CJKBigramFilterFactory"/>
|
514
|
+
</analyzer>
|
515
|
+
</fieldType>
|
516
|
+
|
517
|
+
<!-- Czech -->
|
518
|
+
<fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
|
519
|
+
<analyzer>
|
520
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
521
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
522
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" enablePositionIncrements="true"/>
|
523
|
+
<filter class="solr.CzechStemFilterFactory"/>
|
524
|
+
</analyzer>
|
525
|
+
</fieldType>
|
526
|
+
|
527
|
+
<!-- Danish -->
|
528
|
+
<fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
|
529
|
+
<analyzer>
|
530
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
531
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
532
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" enablePositionIncrements="true"/>
|
533
|
+
<filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
|
534
|
+
</analyzer>
|
535
|
+
</fieldType>
|
536
|
+
|
537
|
+
<!-- German -->
|
538
|
+
<fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
|
539
|
+
<analyzer>
|
540
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
541
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
542
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" enablePositionIncrements="true"/>
|
543
|
+
<filter class="solr.GermanNormalizationFilterFactory"/>
|
544
|
+
<filter class="solr.GermanLightStemFilterFactory"/>
|
545
|
+
<!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
|
546
|
+
<!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
|
547
|
+
</analyzer>
|
548
|
+
</fieldType>
|
549
|
+
|
550
|
+
<!-- Greek -->
|
551
|
+
<fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
|
552
|
+
<analyzer>
|
553
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
554
|
+
<!-- greek specific lowercase for sigma -->
|
555
|
+
<filter class="solr.GreekLowerCaseFilterFactory"/>
|
556
|
+
<filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" enablePositionIncrements="true"/>
|
557
|
+
<filter class="solr.GreekStemFilterFactory"/>
|
558
|
+
</analyzer>
|
559
|
+
</fieldType>
|
560
|
+
|
561
|
+
<!-- Spanish -->
|
562
|
+
<fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
|
563
|
+
<analyzer>
|
564
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
565
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
566
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" enablePositionIncrements="true"/>
|
567
|
+
<filter class="solr.SpanishLightStemFilterFactory"/>
|
568
|
+
<!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
|
569
|
+
</analyzer>
|
570
|
+
</fieldType>
|
571
|
+
|
572
|
+
<!-- Basque -->
|
573
|
+
<fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
|
574
|
+
<analyzer>
|
575
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
576
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
577
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" enablePositionIncrements="true"/>
|
578
|
+
<filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
|
579
|
+
</analyzer>
|
580
|
+
</fieldType>
|
581
|
+
|
582
|
+
<!-- Persian -->
|
583
|
+
<fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
|
584
|
+
<analyzer>
|
585
|
+
<!-- for ZWNJ -->
|
586
|
+
<charFilter class="solr.PersianCharFilterFactory"/>
|
587
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
588
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
589
|
+
<filter class="solr.ArabicNormalizationFilterFactory"/>
|
590
|
+
<filter class="solr.PersianNormalizationFilterFactory"/>
|
591
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" enablePositionIncrements="true"/>
|
592
|
+
</analyzer>
|
593
|
+
</fieldType>
|
594
|
+
|
595
|
+
<!-- Finnish -->
|
596
|
+
<fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
|
597
|
+
<analyzer>
|
598
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
599
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
600
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" enablePositionIncrements="true"/>
|
601
|
+
<filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
|
602
|
+
<!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
|
603
|
+
</analyzer>
|
604
|
+
</fieldType>
|
605
|
+
|
606
|
+
<!-- French -->
|
607
|
+
<fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
|
608
|
+
<analyzer>
|
609
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
610
|
+
<!-- removes l', etc -->
|
611
|
+
<filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
|
612
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
613
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" enablePositionIncrements="true"/>
|
614
|
+
<filter class="solr.FrenchLightStemFilterFactory"/>
|
615
|
+
<!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
|
616
|
+
<!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
|
617
|
+
</analyzer>
|
618
|
+
</fieldType>
|
619
|
+
|
620
|
+
<!-- Irish -->
|
621
|
+
<fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
|
622
|
+
<analyzer>
|
623
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
624
|
+
<!-- removes d', etc -->
|
625
|
+
<filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
|
626
|
+
<!-- removes n-, etc. position increments is intentionally false! -->
|
627
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt" enablePositionIncrements="false"/>
|
628
|
+
<filter class="solr.IrishLowerCaseFilterFactory"/>
|
629
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt" enablePositionIncrements="true"/>
|
630
|
+
<filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
|
631
|
+
</analyzer>
|
632
|
+
</fieldType>
|
633
|
+
|
634
|
+
<!-- Galician -->
|
635
|
+
<fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
|
636
|
+
<analyzer>
|
637
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
638
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
639
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" enablePositionIncrements="true"/>
|
640
|
+
<filter class="solr.GalicianStemFilterFactory"/>
|
641
|
+
<!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
|
642
|
+
</analyzer>
|
643
|
+
</fieldType>
|
644
|
+
|
645
|
+
<!-- Hindi -->
|
646
|
+
<fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
|
647
|
+
<analyzer>
|
648
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
649
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
650
|
+
<!-- normalizes unicode representation -->
|
651
|
+
<filter class="solr.IndicNormalizationFilterFactory"/>
|
652
|
+
<!-- normalizes variation in spelling -->
|
653
|
+
<filter class="solr.HindiNormalizationFilterFactory"/>
|
654
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" enablePositionIncrements="true"/>
|
655
|
+
<filter class="solr.HindiStemFilterFactory"/>
|
656
|
+
</analyzer>
|
657
|
+
</fieldType>
|
658
|
+
|
659
|
+
<!-- Hungarian -->
|
660
|
+
<fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
|
661
|
+
<analyzer>
|
662
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
663
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
664
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" enablePositionIncrements="true"/>
|
665
|
+
<filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
|
666
|
+
<!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
|
667
|
+
</analyzer>
|
668
|
+
</fieldType>
|
669
|
+
|
670
|
+
<!-- Armenian -->
|
671
|
+
<fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
|
672
|
+
<analyzer>
|
673
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
674
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
675
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" enablePositionIncrements="true"/>
|
676
|
+
<filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
|
677
|
+
</analyzer>
|
678
|
+
</fieldType>
|
679
|
+
|
680
|
+
<!-- Indonesian -->
|
681
|
+
<fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
|
682
|
+
<analyzer>
|
683
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
684
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
685
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" enablePositionIncrements="true"/>
|
686
|
+
<!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
|
687
|
+
<filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
|
688
|
+
</analyzer>
|
689
|
+
</fieldType>
|
690
|
+
|
691
|
+
<!-- Italian -->
|
692
|
+
<fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
|
693
|
+
<analyzer>
|
694
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
695
|
+
<!-- removes l', etc -->
|
696
|
+
<filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
|
697
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
698
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" enablePositionIncrements="true"/>
|
699
|
+
<filter class="solr.ItalianLightStemFilterFactory"/>
|
700
|
+
<!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
|
701
|
+
</analyzer>
|
702
|
+
</fieldType>
|
703
|
+
|
704
|
+
<!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
|
705
|
+
|
706
|
+
NOTE: If you want to optimize search for precision, use default operator AND in your query
|
707
|
+
parser config with <solrQueryParser defaultOperator="AND"/> further down in this file. Use
|
708
|
+
OR if you would like to optimize for recall (default).
|
709
|
+
-->
|
710
|
+
<fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
|
711
|
+
<analyzer>
|
712
|
+
<!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
|
713
|
+
|
714
|
+
Kuromoji has a search mode (default) that does segmentation useful for search. A heuristic
|
715
|
+
is used to segment compounds into its parts and the compound itself is kept as synonym.
|
716
|
+
|
717
|
+
Valid values for attribute mode are:
|
718
|
+
normal: regular segmentation
|
719
|
+
search: segmentation useful for search with synonyms compounds (default)
|
720
|
+
extended: same as search mode, but unigrams unknown words (experimental)
|
721
|
+
|
722
|
+
For some applications it might be good to use search mode for indexing and normal mode for
|
723
|
+
queries to reduce recall and prevent parts of compounds from being matched and highlighted.
|
724
|
+
Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
|
725
|
+
|
726
|
+
Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
|
727
|
+
model with your own entries for segmentation, part-of-speech tags and readings without a need
|
728
|
+
to specify weights. Notice that user dictionaries have not been subject to extensive testing.
|
729
|
+
|
730
|
+
User dictionary attributes are:
|
731
|
+
userDictionary: user dictionary filename
|
732
|
+
userDictionaryEncoding: user dictionary encoding (default is UTF-8)
|
733
|
+
|
734
|
+
See lang/userdict_ja.txt for a sample user dictionary file.
|
735
|
+
|
736
|
+
Punctuation characters are discarded by default. Use discardPunctuation="false" to keep them.
|
737
|
+
|
738
|
+
See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
|
739
|
+
-->
|
740
|
+
<tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
|
741
|
+
<!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
|
742
|
+
<!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
|
743
|
+
<filter class="solr.JapaneseBaseFormFilterFactory"/>
|
744
|
+
<!-- Removes tokens with certain part-of-speech tags -->
|
745
|
+
<filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" enablePositionIncrements="true"/>
|
746
|
+
<!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
|
747
|
+
<filter class="solr.CJKWidthFilterFactory"/>
|
748
|
+
<!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
|
749
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" enablePositionIncrements="true" />
|
750
|
+
<!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
|
751
|
+
<filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
|
752
|
+
<!-- Lower-cases romaji characters -->
|
753
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
754
|
+
</analyzer>
|
755
|
+
</fieldType>
|
756
|
+
|
757
|
+
<!-- Latvian -->
|
758
|
+
<fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
|
759
|
+
<analyzer>
|
760
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
761
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
762
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" enablePositionIncrements="true"/>
|
763
|
+
<filter class="solr.LatvianStemFilterFactory"/>
|
764
|
+
</analyzer>
|
765
|
+
</fieldType>
|
766
|
+
|
767
|
+
<!-- Dutch -->
|
768
|
+
<fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
|
769
|
+
<analyzer>
|
770
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
771
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
772
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" enablePositionIncrements="true"/>
|
773
|
+
<filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
|
774
|
+
<filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
|
775
|
+
</analyzer>
|
776
|
+
</fieldType>
|
777
|
+
|
778
|
+
<!-- Norwegian -->
|
779
|
+
<fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
|
780
|
+
<analyzer>
|
781
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
782
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
783
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" enablePositionIncrements="true"/>
|
784
|
+
<filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
|
785
|
+
<!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> -->
|
786
|
+
<!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
|
787
|
+
</analyzer>
|
788
|
+
</fieldType>
|
789
|
+
|
790
|
+
<!-- Portuguese -->
|
791
|
+
<fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
|
792
|
+
<analyzer>
|
793
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
794
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
795
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" enablePositionIncrements="true"/>
|
796
|
+
<filter class="solr.PortugueseLightStemFilterFactory"/>
|
797
|
+
<!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
|
798
|
+
<!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
|
799
|
+
<!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
|
800
|
+
</analyzer>
|
801
|
+
</fieldType>
|
802
|
+
|
803
|
+
<!-- Romanian -->
|
804
|
+
<fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
|
805
|
+
<analyzer>
|
806
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
807
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
808
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" enablePositionIncrements="true"/>
|
809
|
+
<filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
|
810
|
+
</analyzer>
|
811
|
+
</fieldType>
|
812
|
+
|
813
|
+
<!-- Russian -->
|
814
|
+
<fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
|
815
|
+
<analyzer>
|
816
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
817
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
818
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" enablePositionIncrements="true"/>
|
819
|
+
<filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
|
820
|
+
<!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
|
821
|
+
</analyzer>
|
822
|
+
</fieldType>
|
823
|
+
|
824
|
+
<!-- Swedish -->
|
825
|
+
<fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
|
826
|
+
<analyzer>
|
827
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
828
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
829
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" enablePositionIncrements="true"/>
|
830
|
+
<filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
|
831
|
+
<!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
|
832
|
+
</analyzer>
|
833
|
+
</fieldType>
|
834
|
+
|
835
|
+
<!-- Thai -->
|
836
|
+
<fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
|
837
|
+
<analyzer>
|
838
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
839
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
840
|
+
<filter class="solr.ThaiWordFilterFactory"/>
|
841
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" enablePositionIncrements="true"/>
|
842
|
+
</analyzer>
|
843
|
+
</fieldType>
|
844
|
+
|
845
|
+
<!-- Turkish -->
|
846
|
+
<fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
|
847
|
+
<analyzer>
|
848
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
849
|
+
<filter class="solr.TurkishLowerCaseFilterFactory"/>
|
850
|
+
<filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" enablePositionIncrements="true"/>
|
851
|
+
<filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
|
852
|
+
</analyzer>
|
853
|
+
</fieldType>
|
854
|
+
</types>
|
855
|
+
|
856
|
+
<fields>
|
857
|
+
|
858
|
+
<!-- NOTE: this is not a full list of fields in the index; dynamic fields are also used -->
|
859
|
+
<field name="id" type="string" indexed="true" stored="true" required="true" />
|
860
|
+
<field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
|
861
|
+
<!-- default, catch all search field -->
|
862
|
+
<field name="text" type="text_en" indexed="true" stored="false" multiValued="true"/>
|
863
|
+
|
864
|
+
<!-- these display fields are NOT multi-valued -->
|
865
|
+
<field name="marc_display" type="string" indexed="false" stored="true" multiValued="false" />
|
866
|
+
<field name="heading_display" type="string" indexed="false" stored="true" multiValued="false" />
|
867
|
+
<field name="title_display" type="text_en" indexed="false" stored="true" multiValued="false" />
|
868
|
+
<field name="title_vern_display" type="text_en" indexed="false" stored="true" multiValued="false" />
|
869
|
+
<field name="subtitle_display" type="text_en" indexed="false" stored="true" multiValued="false" />
|
870
|
+
<field name="subtitle_vern_display" type="text_en" indexed="false" stored="true" multiValued="false" />
|
871
|
+
<field name="author_display" type="text_en" indexed="false" stored="true" multiValued="false" />
|
872
|
+
<field name="author_vern_display" type="text_en" indexed="false" stored="true" multiValued="false" />
|
873
|
+
|
874
|
+
<!-- by default, facet fields are not stored, so they may be display differenty than the are
|
875
|
+
indexed. Here are the exceptions to this, which are facet fields that are displayed the
|
876
|
+
same as they are indexed -->
|
877
|
+
<field name="subject_facet" type="string" indexed="true" stored="true" multiValued="true" />
|
878
|
+
<field name="pub_date" type="string" indexed="true" stored="true" multiValued="true" />
|
879
|
+
<field name="genre_facet" type="string" indexed="true" stored="true" multiValued="true" />
|
880
|
+
<field name="collection_facet" type="string" indexed="true" stored="true" multiValued="true" />
|
881
|
+
|
882
|
+
<!-- pub_date_sort uses new trie-based int fields, which are recommended for any int and are
|
883
|
+
displayable, sortable, and can be used in range queries.
|
884
|
+
Use 'tint' for faster range-queries. -->
|
885
|
+
<field name="pub_date_sort" type="tint" indexed="true" stored="true" multiValued="false"/>
|
886
|
+
|
887
|
+
<!-- format is used for facet, display, and choosing which partial to use for the show view,
|
888
|
+
so it must be stored and indexed -->
|
889
|
+
<field name="format" type="string" indexed="true" stored="true"/>
|
890
|
+
|
891
|
+
<!-- Dynamic field definitions. If a field name is not found, dynamicFields
|
892
|
+
will be used if the name matches any of the patterns.
|
893
|
+
RESTRICTION: the glob-like pattern in the name attribute must have
|
894
|
+
a "*" only at the start or the end.
|
895
|
+
EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
|
896
|
+
Longer patterns will be matched first. if equal size patterns
|
897
|
+
both match, the first appearing in the schema will be used. -->
|
898
|
+
<dynamicField name="*_i" type="int" indexed="true" stored="true" multiValued="false" />
|
899
|
+
<dynamicField name="*_s" type="string" indexed="true" stored="true" multiValued="true" />
|
900
|
+
<dynamicField name="*_id" type="string" indexed="true" stored="true" multiValued="false" />
|
901
|
+
<dynamicField name="*_l" type="long" indexed="true" stored="true" multiValued="false" />
|
902
|
+
<dynamicField name="*_t" type="text_en" indexed="true" stored="false" multiValued="true" />
|
903
|
+
<dynamicField name="*_txt" type="text_general" indexed="true" stored="true" multiValued="true" />
|
904
|
+
<dynamicField name="*_b" type="boolean" indexed="true" stored="true" multiValued="false" />
|
905
|
+
<dynamicField name="*_f" type="float" indexed="true" stored="true" multiValued="false" />
|
906
|
+
<dynamicField name="*_d" type="double" indexed="true" stored="true" multiValued="false" />
|
907
|
+
<dynamicField name="*_display" type="text_en" indexed="false" stored="true" multiValued="true" />
|
908
|
+
<dynamicField name="*_label" type="string" indexed="false" stored="true" multiValued="true" />
|
909
|
+
<dynamicField name="*_facet" type="string" indexed="true" stored="false" multiValued="true" />
|
910
|
+
<dynamicField name="*_sort" type="alphaOnlySort" indexed="true" stored="false" multiValued="false" />
|
911
|
+
<dynamicField name="*_unstem_search" type="text_general" indexed="true" stored="false" multiValued="true" />
|
912
|
+
<dynamicField name="*spell" type="textSpell" indexed="true" stored="false" multiValued="true" />
|
913
|
+
<dynamicField name="*_dt" type="date" indexed="true" stored="true" multiValued="false" />
|
914
|
+
<dynamicField name="*_dts" type="date" indexed="true" stored="true" multiValued="true" />
|
915
|
+
<dynamicField name="*_p" type="location" indexed="true" stored="true" multiValued="false" />
|
916
|
+
|
917
|
+
<!-- Miscellaneous fields -->
|
918
|
+
<dynamicField name="ignored_*" type="ignored" multiValued="true"/>
|
919
|
+
<dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
|
920
|
+
<dynamicField name="random_*" type="random" />
|
921
|
+
|
922
|
+
<dynamicField name="*_ti" type="text_en" stored="false" indexed="true" multiValued="false" />
|
923
|
+
<dynamicField name="*_tim" type="text_en" stored="false" indexed="true" multiValued="true" />
|
924
|
+
<dynamicField name="*_ts" type="text_en" stored="true" indexed="false" multiValued="false" />
|
925
|
+
<dynamicField name="*_tsm" type="text_en" stored="true" indexed="false" multiValued="true" />
|
926
|
+
<dynamicField name="*_tsi" type="text_en" stored="true" indexed="true" multiValued="false" />
|
927
|
+
<dynamicField name="*_tsim" type="text_en" stored="true" indexed="true" multiValued="true" />
|
928
|
+
<dynamicField name="*_tiv" type="text_en" stored="false" indexed="true" multiValued="false" termVectors="true" termPositions="true" termOffsets="true"/>
|
929
|
+
<dynamicField name="*_timv" type="text_en" stored="false" indexed="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
|
930
|
+
<dynamicField name="*_tsiv" type="text_en" stored="true" indexed="true" multiValued="false" termVectors="true" termPositions="true" termOffsets="true"/>
|
931
|
+
<dynamicField name="*_tsimv" type="text_en" stored="true" indexed="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
|
932
|
+
|
933
|
+
<!-- English text (_te...) -->
|
934
|
+
<dynamicField name="*_tei" type="text_en" stored="false" indexed="true" multiValued="false" />
|
935
|
+
<dynamicField name="*_teim" type="text_en" stored="false" indexed="true" multiValued="true" />
|
936
|
+
<dynamicField name="*_tes" type="text_en" stored="true" indexed="false" multiValued="false" />
|
937
|
+
<dynamicField name="*_tesm" type="text_en" stored="true" indexed="false" multiValued="true" />
|
938
|
+
<dynamicField name="*_tesi" type="text_en" stored="true" indexed="true" multiValued="false" />
|
939
|
+
<dynamicField name="*_tesim" type="text_en" stored="true" indexed="true" multiValued="true" />
|
940
|
+
<dynamicField name="*_teiv" type="text_en" stored="false" indexed="true" multiValued="false" termVectors="true" termPositions="true" termOffsets="true"/>
|
941
|
+
<dynamicField name="*_teimv" type="text_en" stored="false" indexed="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
|
942
|
+
<dynamicField name="*_tesiv" type="text_en" stored="true" indexed="true" multiValued="false" termVectors="true" termPositions="true" termOffsets="true"/>
|
943
|
+
<dynamicField name="*_tesimv" type="text_en" stored="true" indexed="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
|
944
|
+
|
945
|
+
<!-- string (_s...) -->
|
946
|
+
<dynamicField name="*_si" type="string" stored="false" indexed="true" multiValued="false" />
|
947
|
+
<dynamicField name="*_sim" type="string" stored="false" indexed="true" multiValued="true" />
|
948
|
+
<dynamicField name="*_ss" type="string" stored="true" indexed="false" multiValued="false" />
|
949
|
+
<dynamicField name="*_ssm" type="string" stored="true" indexed="false" multiValued="true" />
|
950
|
+
<dynamicField name="*_ssi" type="string" stored="true" indexed="true" multiValued="false" />
|
951
|
+
<dynamicField name="*_ssim" type="string" stored="true" indexed="true" multiValued="true" />
|
952
|
+
<dynamicField name="*_ssort" type="alphaSort" stored="false" indexed="true" multiValued="false" />
|
953
|
+
|
954
|
+
<!-- integer (_i...) -->
|
955
|
+
<dynamicField name="*_ii" type="int" stored="false" indexed="true" multiValued="false" />
|
956
|
+
<dynamicField name="*_iim" type="int" stored="false" indexed="true" multiValued="true" />
|
957
|
+
<dynamicField name="*_is" type="int" stored="true" indexed="false" multiValued="false" />
|
958
|
+
<dynamicField name="*_ism" type="int" stored="true" indexed="false" multiValued="true" />
|
959
|
+
<dynamicField name="*_isi" type="int" stored="true" indexed="true" multiValued="false" />
|
960
|
+
<dynamicField name="*_isim" type="int" stored="true" indexed="true" multiValued="true" />
|
961
|
+
|
962
|
+
<!-- trie integer (_it...) (for faster range queries) -->
|
963
|
+
<dynamicField name="*_iti" type="tint" stored="false" indexed="true" multiValued="false" />
|
964
|
+
<dynamicField name="*_itim" type="tint" stored="false" indexed="true" multiValued="true" />
|
965
|
+
<dynamicField name="*_its" type="tint" stored="true" indexed="false" multiValued="false" />
|
966
|
+
<dynamicField name="*_itsm" type="tint" stored="true" indexed="false" multiValued="true" />
|
967
|
+
<dynamicField name="*_itsi" type="tint" stored="true" indexed="true" multiValued="false" />
|
968
|
+
<dynamicField name="*_itsim" type="tint" stored="true" indexed="true" multiValued="true" />
|
969
|
+
|
970
|
+
<!-- date (_dt...) -->
|
971
|
+
<!-- The format for this date field is of the form 1995-12-31T23:59:59Z
|
972
|
+
Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z -->
|
973
|
+
<dynamicField name="*_dti" type="date" stored="false" indexed="true" multiValued="false" />
|
974
|
+
<dynamicField name="*_dtim" type="date" stored="false" indexed="true" multiValued="true" />
|
975
|
+
<dynamicField name="*_dts" type="date" stored="true" indexed="false" multiValued="false" />
|
976
|
+
<dynamicField name="*_dtsm" type="date" stored="true" indexed="false" multiValued="true" />
|
977
|
+
<dynamicField name="*_dtsi" type="date" stored="true" indexed="true" multiValued="false" />
|
978
|
+
<dynamicField name="*_dtsim" type="date" stored="true" indexed="true" multiValued="true" />
|
979
|
+
|
980
|
+
<!-- trie date (_dtt...) (for faster range queries) -->
|
981
|
+
<dynamicField name="*_dtti" type="tdate" stored="false" indexed="true" multiValued="false" />
|
982
|
+
<dynamicField name="*_dttim" type="tdate" stored="false" indexed="true" multiValued="true" />
|
983
|
+
<dynamicField name="*_dtts" type="tdate" stored="true" indexed="false" multiValued="false" />
|
984
|
+
<dynamicField name="*_dttsm" type="tdate" stored="true" indexed="false" multiValued="true" />
|
985
|
+
<dynamicField name="*_dttsi" type="tdate" stored="true" indexed="true" multiValued="false" />
|
986
|
+
<dynamicField name="*_dttsim" type="tdate" stored="true" indexed="true" multiValued="true" />
|
987
|
+
|
988
|
+
<!-- long (_l...) -->
|
989
|
+
<dynamicField name="*_li" type="long" stored="false" indexed="true" multiValued="false" />
|
990
|
+
<dynamicField name="*_lim" type="long" stored="false" indexed="true" multiValued="true" />
|
991
|
+
<dynamicField name="*_ls" type="long" stored="true" indexed="false" multiValued="false" />
|
992
|
+
<dynamicField name="*_lsm" type="long" stored="true" indexed="false" multiValued="true" />
|
993
|
+
<dynamicField name="*_lsi" type="long" stored="true" indexed="true" multiValued="false" />
|
994
|
+
<dynamicField name="*_lsim" type="long" stored="true" indexed="true" multiValued="true" />
|
995
|
+
|
996
|
+
<!-- trie long (_lt...) (for faster range queries) -->
|
997
|
+
<dynamicField name="*_lti" type="tlong" stored="false" indexed="true" multiValued="false" />
|
998
|
+
<dynamicField name="*_ltim" type="tlong" stored="false" indexed="true" multiValued="true" />
|
999
|
+
<dynamicField name="*_lts" type="tlong" stored="true" indexed="false" multiValued="false" />
|
1000
|
+
<dynamicField name="*_ltsm" type="tlong" stored="true" indexed="false" multiValued="true" />
|
1001
|
+
<dynamicField name="*_ltsi" type="tlong" stored="true" indexed="true" multiValued="false" />
|
1002
|
+
<dynamicField name="*_ltsim" type="tlong" stored="true" indexed="true" multiValued="true" />
|
1003
|
+
|
1004
|
+
<!-- double (_db...) -->
|
1005
|
+
<dynamicField name="*_dbi" type="double" stored="false" indexed="true" multiValued="false" />
|
1006
|
+
<dynamicField name="*_dbim" type="double" stored="false" indexed="true" multiValued="true" />
|
1007
|
+
<dynamicField name="*_dbs" type="double" stored="true" indexed="false" multiValued="false" />
|
1008
|
+
<dynamicField name="*_dbsm" type="double" stored="true" indexed="false" multiValued="true" />
|
1009
|
+
<dynamicField name="*_dbsi" type="double" stored="true" indexed="true" multiValued="false" />
|
1010
|
+
<dynamicField name="*_dbsim" type="double" stored="true" indexed="true" multiValued="true" />
|
1011
|
+
|
1012
|
+
<!-- trie double (_dbt...) (for faster range queries) -->
|
1013
|
+
<dynamicField name="*_dbti" type="tdouble" stored="false" indexed="true" multiValued="false" />
|
1014
|
+
<dynamicField name="*_dbtim" type="tdouble" stored="false" indexed="true" multiValued="true" />
|
1015
|
+
<dynamicField name="*_dbts" type="tdouble" stored="true" indexed="false" multiValued="false" />
|
1016
|
+
<dynamicField name="*_dbtsm" type="tdouble" stored="true" indexed="false" multiValued="true" />
|
1017
|
+
<dynamicField name="*_dbtsi" type="tdouble" stored="true" indexed="true" multiValued="false" />
|
1018
|
+
<dynamicField name="*_dbtsim" type="tdouble" stored="true" indexed="true" multiValued="true" />
|
1019
|
+
|
1020
|
+
<!-- float (_f...) -->
|
1021
|
+
<dynamicField name="*_fi" type="float" stored="false" indexed="true" multiValued="false" />
|
1022
|
+
<dynamicField name="*_fim" type="float" stored="false" indexed="true" multiValued="true" />
|
1023
|
+
<dynamicField name="*_fs" type="float" stored="true" indexed="false" multiValued="false" />
|
1024
|
+
<dynamicField name="*_fsm" type="float" stored="true" indexed="false" multiValued="true" />
|
1025
|
+
<dynamicField name="*_fsi" type="float" stored="true" indexed="true" multiValued="false" />
|
1026
|
+
<dynamicField name="*_fsim" type="float" stored="true" indexed="true" multiValued="true" />
|
1027
|
+
|
1028
|
+
<!-- trie float (_ft...) (for faster range queries) -->
|
1029
|
+
<dynamicField name="*_fti" type="tfloat" stored="false" indexed="true" multiValued="false" />
|
1030
|
+
<dynamicField name="*_ftim" type="tfloat" stored="false" indexed="true" multiValued="true" />
|
1031
|
+
<dynamicField name="*_fts" type="tfloat" stored="true" indexed="false" multiValued="false" />
|
1032
|
+
<dynamicField name="*_ftsm" type="tfloat" stored="true" indexed="false" multiValued="true" />
|
1033
|
+
<dynamicField name="*_ftsi" type="tfloat" stored="true" indexed="true" multiValued="false" />
|
1034
|
+
<dynamicField name="*_ftsim" type="tfloat" stored="true" indexed="true" multiValued="true" />
|
1035
|
+
|
1036
|
+
<!-- boolean (_b...) -->
|
1037
|
+
<dynamicField name="*_bi" type="boolean" stored="false" indexed="true" multiValued="false" />
|
1038
|
+
<dynamicField name="*_bs" type="boolean" stored="true" indexed="false" multiValued="false" />
|
1039
|
+
<dynamicField name="*_bsi" type="boolean" stored="true" indexed="true" multiValued="false" />
|
1040
|
+
|
1041
|
+
<!-- Type used to index the lat and lon components for the "location" FieldType -->
|
1042
|
+
<dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false" />
|
1043
|
+
|
1044
|
+
<!-- location (_ll...) -->
|
1045
|
+
<dynamicField name="*_lli" type="location" stored="false" indexed="true" multiValued="false" />
|
1046
|
+
<dynamicField name="*_llim" type="location" stored="false" indexed="true" multiValued="true" />
|
1047
|
+
<dynamicField name="*_lls" type="location" stored="true" indexed="false" multiValued="false" />
|
1048
|
+
<dynamicField name="*_llsm" type="location" stored="true" indexed="false" multiValued="true" />
|
1049
|
+
<dynamicField name="*_llsi" type="location" stored="true" indexed="true" multiValued="false" />
|
1050
|
+
<dynamicField name="*_llsim" type="location" stored="true" indexed="true" multiValued="true" />
|
1051
|
+
|
1052
|
+
<!-- uncomment the following to ignore any fields that don't already match an existing
|
1053
|
+
field name or dynamic field, rather than reporting them as an error.
|
1054
|
+
alternately, change the type="ignored" to some other type e.g. "text" if you want
|
1055
|
+
unknown fields indexed and/or stored by default -->
|
1056
|
+
<!-- dynamicField name="*" type="ignored" multiValued="true" /-->
|
1057
|
+
</fields>
|
1058
|
+
|
1059
|
+
<!-- Field to use to determine and enforce document uniqueness.
|
1060
|
+
Unless this field is marked with required="false", it will be a required field -->
|
1061
|
+
<uniqueKey>id</uniqueKey>
|
1062
|
+
|
1063
|
+
<!-- field for the QueryParser to use when an explicit fieldname is absent -->
|
1064
|
+
<defaultSearchField>text</defaultSearchField>
|
1065
|
+
|
1066
|
+
<!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
|
1067
|
+
<solrQueryParser defaultOperator="OR"/>
|
1068
|
+
|
1069
|
+
<!-- copyField commands copy one field to another at the time a document
|
1070
|
+
is added to the index. It's used either to index the same field differently,
|
1071
|
+
or to add multiple fields to the same field for easier/faster searching. -->
|
1072
|
+
<!-- Copy Fields -->
|
1073
|
+
|
1074
|
+
<!-- unstemmed fields -->
|
1075
|
+
<copyField source="title_t" dest="title_unstem_search"/>
|
1076
|
+
<copyField source="subtitle_t" dest="subtitle_unstem_search"/>
|
1077
|
+
<copyField source="title_addl_t" dest="title_addl_unstem_search"/>
|
1078
|
+
<copyField source="title_added_entry_t" dest="title_added_entry_unstem_search"/>
|
1079
|
+
<copyField source="title_series_t" dest="title_series_unstem_search"/>
|
1080
|
+
<copyField source="author_t" dest="author_unstem_search"/>
|
1081
|
+
<copyField source="author_addl_t" dest="author_addl_unstem_search"/>
|
1082
|
+
<copyField source="subject_t" dest="subject_unstem_search"/>
|
1083
|
+
<copyField source="subject_facet" dest="subject_unstem_search"/>
|
1084
|
+
<copyField source="contributors_t" dest="contributors_unstem_search"/>
|
1085
|
+
<copyField source="lc_callnum_display" dest="lc_callnum_unstem_search"/>
|
1086
|
+
|
1087
|
+
<!-- display fields that are copied to the text field for searching -->
|
1088
|
+
<copyField source="isbn_display" dest="text"/>
|
1089
|
+
|
1090
|
+
<!-- sort fields -->
|
1091
|
+
<copyField source="pub_date" dest="pub_date_sort"/>
|
1092
|
+
|
1093
|
+
<!-- spellcheck fields -->
|
1094
|
+
<!-- default spell check; should match fields for default request handler -->
|
1095
|
+
<!-- it won't work with a copy of a copy field -->
|
1096
|
+
<copyField source="*_t" dest="spell" />
|
1097
|
+
<copyField source="*_facet" dest="spell" />
|
1098
|
+
<!-- title spell check; should match fields for title request handler -->
|
1099
|
+
<copyField source="title_t" dest="title_spell" />
|
1100
|
+
<copyField source="subtitle_t" dest="title_spell" />
|
1101
|
+
<copyField source="addl_titles_t" dest="title_spell" />
|
1102
|
+
<copyField source="title_added_entry_t" dest="title_spell" />
|
1103
|
+
<copyField source="title_series_t" dest="title_spell" />
|
1104
|
+
<!-- author spell check; should match fields for author request handler -->
|
1105
|
+
<copyField source="author_t" dest="name_spell" />
|
1106
|
+
<copyField source="author_addl_t" dest="name_spell" />
|
1107
|
+
<!-- subject spell check; should match fields for subject request handler -->
|
1108
|
+
<copyField source="subject_facet" dest="subject_spell" />
|
1109
|
+
<copyField source="subject_t" dest="subject_spell" />
|
1110
|
+
<!-- contributor and genre spell check -->
|
1111
|
+
<copyField source="contributors_t" dest="name_spell" />
|
1112
|
+
<copyField source="genre_t" dest="genre_spell" />
|
1113
|
+
|
1114
|
+
<!-- OpenSearch query field should match request handler search fields -->
|
1115
|
+
<copyField source="title_t" dest="opensearch_display" />
|
1116
|
+
<copyField source="subtitle_t" dest="opensearch_display" />
|
1117
|
+
<copyField source="addl_titles_t" dest="opensearch_display" />
|
1118
|
+
<copyField source="title_added_entry_t" dest="opensearch_display" />
|
1119
|
+
<copyField source="title_series_t" dest="opensearch_display" />
|
1120
|
+
<copyField source="author_t" dest="opensearch_display" />
|
1121
|
+
<copyField source="author_addl_t" dest="opensearch_display" />
|
1122
|
+
<copyField source="subject_facet" dest="opensearch_display" />
|
1123
|
+
<copyField source="subject_t" dest="opensearch_display" />
|
1124
|
+
|
1125
|
+
<!-- Copy over all of Hydra dynamic fields to Blacklight's -->
|
1126
|
+
<copyField source="*_dtsi" dest="*_dt" />
|
1127
|
+
<copyField source="*_teim" dest="*_t" />
|
1128
|
+
<copyField source="*_si" dest="*_t" />
|
1129
|
+
<copyField source="*_sim" dest="*_t" />
|
1130
|
+
<copyField source="*_ssi" dest="*_t" />
|
1131
|
+
<copyField source="*_ssim" dest="*_t" />
|
1132
|
+
<copyField source="*_dtsi" dest="*_t" />
|
1133
|
+
<copyField source="*_dtsim" dest="*_t" />
|
1134
|
+
<copyField source="*_ssm" dest="*_display" />
|
1135
|
+
<copyField source="*_ssi" dest="*_display" />
|
1136
|
+
<copyField source="*_ssim" dest="*_display" />
|
1137
|
+
<copyField source="*_dtsi" dest="*_display" />
|
1138
|
+
<copyField source="*_dtsim" dest="*_display" />
|
1139
|
+
|
1140
|
+
|
1141
|
+
<!-- Above, multiple source fields are copied to the [text] field.
|
1142
|
+
Another way to map multiple source fields to the same
|
1143
|
+
destination field is to use the dynamic field syntax.
|
1144
|
+
copyField also supports a maxChars to copy setting. -->
|
1145
|
+
|
1146
|
+
<!-- <copyField source="*_t" dest="text" maxChars="3000"/> -->
|
1147
|
+
|
1148
|
+
<!-- copy name to alphaNameSort, a field designed for sorting by name -->
|
1149
|
+
<!-- <copyField source="name" dest="alphaNameSort"/> -->
|
1150
|
+
|
1151
|
+
|
1152
|
+
<!-- Similarity is the scoring routine for each document vs. a query.
|
1153
|
+
A custom Similarity or SimilarityFactory may be specified here, but
|
1154
|
+
the default is fine for most applications.
|
1155
|
+
For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
|
1156
|
+
-->
|
1157
|
+
<!--
|
1158
|
+
<similarity class="com.example.solr.CustomSimilarityFactory">
|
1159
|
+
<str name="paramkey">param value</str>
|
1160
|
+
</similarity>
|
1161
|
+
-->
|
1162
|
+
|
1163
|
+
</schema>
|