krikri 0.12.1 → 0.12.3
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/generators/krikri/templates/schema.xml +767 -0
- data/lib/generators/krikri/templates/solrconfig.xml +160 -0
- data/lib/krikri/async_uri_getter.rb +19 -14
- data/lib/krikri/version.rb +1 -1
- data/spec/lib/krikri/async_uri_getter_spec.rb +11 -0
- metadata +4 -3
- data/lib/generators/krikri/templates/schema.xml +0 -1
- data/lib/generators/krikri/templates/solrconfig.xml +0 -1
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: af1ac47d3d861edd6eb88da136736645598d4040
|
|
4
|
+
data.tar.gz: cd4dc4745a8535311347af768da3864272ba8cda
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: c64131af7a6bace61f13a53c92678b78e16f1547295731f563b46ab45f634671522a1c7134a240b0c8dcc6712acced9b3ede00b1bce9ec290e46064dd5360a34
|
|
7
|
+
data.tar.gz: 6ed7589fc0586bf1e3c0b55c589fc64582bc78a251ac53dc97adc3211e18807fdd435a0fbb2bdb66b9e4d007c1cac7adc52188c831758d7baf28cc7aa4a03067
|
|
@@ -0,0 +1,767 @@
|
|
|
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="DPLA MAPV4.0" version="1.5">
|
|
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="1.5" is Solr's version number for the schema syntax and semantics. It should
|
|
52
|
+
not normally be changed by applications.
|
|
53
|
+
1.0: multiValued attribute did not exist, all fields are multiValued by nature
|
|
54
|
+
1.1: multiValued attribute introduced, false by default
|
|
55
|
+
1.2: omitTermFreqAndPositions attribute introduced, true by default except for text fields.
|
|
56
|
+
1.3: removed optional field compress feature
|
|
57
|
+
1.4: default auto-phrase (QueryParser feature) to off
|
|
58
|
+
-->
|
|
59
|
+
|
|
60
|
+
<types>
|
|
61
|
+
<!-- field type definitions. The "name" attribute is
|
|
62
|
+
just a label to be used by field definitions. The "class"
|
|
63
|
+
attribute and any other attributes determine the real
|
|
64
|
+
behavior of the fieldType.
|
|
65
|
+
Class names starting with "solr" refer to java classes in the
|
|
66
|
+
org.apache.solr.analysis package.
|
|
67
|
+
-->
|
|
68
|
+
|
|
69
|
+
<!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
|
|
70
|
+
<fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
|
|
71
|
+
|
|
72
|
+
<!-- boolean type: "true" or "false" -->
|
|
73
|
+
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
|
|
74
|
+
<!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
|
|
75
|
+
<fieldtype name="binary" class="solr.BinaryField"/>
|
|
76
|
+
|
|
77
|
+
<!-- The optional sortMissingLast and sortMissingFirst attributes are
|
|
78
|
+
v currently supported on types that are sorted internally as strings
|
|
79
|
+
and on numeric types.
|
|
80
|
+
This includes "string","boolean", and, as of 3.5 (and 4.x),
|
|
81
|
+
int, float, long, date, double, including the "Trie" variants.
|
|
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
|
+
<!-- The "RandomSortField" is not used to store or search any
|
|
160
|
+
data. You can declare fields of this type it in your schema
|
|
161
|
+
to generate pseudo-random orderings of your docs for sorting
|
|
162
|
+
purposes. The ordering is generated based on the field name
|
|
163
|
+
and the version of the index, As long as the index version
|
|
164
|
+
remains unchanged, and the same field name is reused,
|
|
165
|
+
the ordering of the docs will be consistent.
|
|
166
|
+
If you want different psuedo-random orderings of documents,
|
|
167
|
+
for the same version of the index, use a dynamicField and
|
|
168
|
+
change the name
|
|
169
|
+
-->
|
|
170
|
+
<fieldType name="random" class="solr.RandomSortField" indexed="true" />
|
|
171
|
+
|
|
172
|
+
<!-- solr.TextField allows the specification of custom text analyzers
|
|
173
|
+
specified as a tokenizer and a list of token filters. Different
|
|
174
|
+
analyzers may be specified for indexing and querying.
|
|
175
|
+
|
|
176
|
+
The optional positionIncrementGap puts space between multiple fields of
|
|
177
|
+
this type on the same document, with the purpose of preventing false phrase
|
|
178
|
+
matching across fields.
|
|
179
|
+
|
|
180
|
+
For more info on customizing your analyzer chain, please see
|
|
181
|
+
http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
|
|
182
|
+
-->
|
|
183
|
+
<fieldType name="text" class="solr.TextField" positionIncrementGap="100">
|
|
184
|
+
<analyzer>
|
|
185
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
186
|
+
<filter class="solr.ICUFoldingFilterFactory" />
|
|
187
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
|
|
188
|
+
<filter class="solr.SnowballPorterFilterFactory" language="English" />
|
|
189
|
+
</analyzer>
|
|
190
|
+
</fieldType>
|
|
191
|
+
|
|
192
|
+
<!-- One can also specify an existing Analyzer class that has a
|
|
193
|
+
default constructor via the class attribute on the analyzer element
|
|
194
|
+
<fieldType name="text_greek" class="solr.TextField">
|
|
195
|
+
<analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
|
|
196
|
+
</fieldType>
|
|
197
|
+
-->
|
|
198
|
+
|
|
199
|
+
<!-- A text field that only splits on whitespace for exact matching of words -->
|
|
200
|
+
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
|
|
201
|
+
<analyzer>
|
|
202
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
203
|
+
</analyzer>
|
|
204
|
+
</fieldType>
|
|
205
|
+
|
|
206
|
+
<!-- A general text field that has reasonable, generic
|
|
207
|
+
cross-language defaults: it tokenizes with StandardTokenizer,
|
|
208
|
+
removes stop words from case-insensitive "stopwords.txt"
|
|
209
|
+
(empty by default), and down cases. At query time only, it
|
|
210
|
+
also applies synonyms. -->
|
|
211
|
+
<fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
|
|
212
|
+
<analyzer type="index">
|
|
213
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
214
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
|
|
215
|
+
<!-- in this example, we will only use synonyms at query time
|
|
216
|
+
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
|
|
217
|
+
-->
|
|
218
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
|
219
|
+
</analyzer>
|
|
220
|
+
<analyzer type="query">
|
|
221
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
222
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
|
|
223
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
|
224
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
|
225
|
+
</analyzer>
|
|
226
|
+
</fieldType>
|
|
227
|
+
|
|
228
|
+
<!-- A text field with defaults appropriate for English: it
|
|
229
|
+
tokenizes with StandardTokenizer, removes English stop words
|
|
230
|
+
(stopwords_en.txt), down cases, protects words from protwords.txt, and
|
|
231
|
+
finally applies Porter's stemming. The query time analyzer
|
|
232
|
+
also applies synonyms from synonyms.txt. -->
|
|
233
|
+
<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
|
|
234
|
+
<analyzer type="index">
|
|
235
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
236
|
+
<!-- in this example, we will only use synonyms at query time
|
|
237
|
+
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
|
|
238
|
+
-->
|
|
239
|
+
<!-- Case insensitive stop word removal.
|
|
240
|
+
add enablePositionIncrements=true in both the index and query
|
|
241
|
+
analyzers to leave a 'gap' for more accurate phrase queries.
|
|
242
|
+
-->
|
|
243
|
+
<filter class="solr.StopFilterFactory"
|
|
244
|
+
ignoreCase="true"
|
|
245
|
+
words="stopwords_en.txt"
|
|
246
|
+
enablePositionIncrements="true"
|
|
247
|
+
/>
|
|
248
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
|
249
|
+
<filter class="solr.EnglishPossessiveFilterFactory"/>
|
|
250
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
|
251
|
+
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
|
|
252
|
+
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
|
253
|
+
-->
|
|
254
|
+
<filter class="solr.PorterStemFilterFactory"/>
|
|
255
|
+
</analyzer>
|
|
256
|
+
<analyzer type="query">
|
|
257
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
258
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
|
259
|
+
<filter class="solr.StopFilterFactory"
|
|
260
|
+
ignoreCase="true"
|
|
261
|
+
words="stopwords_en.txt"
|
|
262
|
+
enablePositionIncrements="true"
|
|
263
|
+
/>
|
|
264
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
|
265
|
+
<filter class="solr.EnglishPossessiveFilterFactory"/>
|
|
266
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
|
267
|
+
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
|
|
268
|
+
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
|
269
|
+
-->
|
|
270
|
+
<filter class="solr.PorterStemFilterFactory"/>
|
|
271
|
+
</analyzer>
|
|
272
|
+
</fieldType>
|
|
273
|
+
|
|
274
|
+
<!-- A text field with defaults appropriate for English, plus
|
|
275
|
+
aggressive word-splitting and autophrase features enabled.
|
|
276
|
+
This field is just like text_en, except it adds
|
|
277
|
+
WordDelimiterFilter to enable splitting and matching of
|
|
278
|
+
words on case-change, alpha numeric boundaries, and
|
|
279
|
+
non-alphanumeric chars. This means certain compound word
|
|
280
|
+
cases will work, for example query "wi fi" will match
|
|
281
|
+
document "WiFi" or "wi-fi". However, other cases will still
|
|
282
|
+
not match, for example if the query is "wifi" and the
|
|
283
|
+
document is "wi fi" or if the query is "wi-fi" and the
|
|
284
|
+
document is "wifi".
|
|
285
|
+
-->
|
|
286
|
+
<fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
|
|
287
|
+
<analyzer type="index">
|
|
288
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
289
|
+
<!-- in this example, we will only use synonyms at query time
|
|
290
|
+
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
|
|
291
|
+
-->
|
|
292
|
+
<!-- Case insensitive stop word removal.
|
|
293
|
+
add enablePositionIncrements=true in both the index and query
|
|
294
|
+
analyzers to leave a 'gap' for more accurate phrase queries.
|
|
295
|
+
-->
|
|
296
|
+
<filter class="solr.StopFilterFactory"
|
|
297
|
+
ignoreCase="true"
|
|
298
|
+
words="stopwords_en.txt"
|
|
299
|
+
enablePositionIncrements="true"
|
|
300
|
+
/>
|
|
301
|
+
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
|
|
302
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
|
303
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
|
304
|
+
<filter class="solr.PorterStemFilterFactory"/>
|
|
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_en.txt"
|
|
312
|
+
enablePositionIncrements="true"
|
|
313
|
+
/>
|
|
314
|
+
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
|
|
315
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
|
316
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
|
317
|
+
<filter class="solr.PorterStemFilterFactory"/>
|
|
318
|
+
</analyzer>
|
|
319
|
+
</fieldType>
|
|
320
|
+
|
|
321
|
+
<!-- Less flexible matching, but less false matches. Probably not ideal for product names,
|
|
322
|
+
but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
|
|
323
|
+
<fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
|
|
324
|
+
<analyzer>
|
|
325
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
326
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
|
|
327
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_en.txt"/>
|
|
328
|
+
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
|
|
329
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
|
330
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
|
331
|
+
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
|
332
|
+
<!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
|
|
333
|
+
possible with WordDelimiterFilter in conjuncton with stemming. -->
|
|
334
|
+
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
335
|
+
</analyzer>
|
|
336
|
+
</fieldType>
|
|
337
|
+
|
|
338
|
+
<!-- Just like text_general except it reverses the characters of
|
|
339
|
+
each token, to enable more efficient leading wildcard queries. -->
|
|
340
|
+
<fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
|
|
341
|
+
<analyzer type="index">
|
|
342
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
343
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
|
|
344
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
|
345
|
+
<filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
|
|
346
|
+
maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
|
|
347
|
+
</analyzer>
|
|
348
|
+
<analyzer type="query">
|
|
349
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
350
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
|
351
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
|
|
352
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
|
353
|
+
</analyzer>
|
|
354
|
+
</fieldType>
|
|
355
|
+
|
|
356
|
+
<fieldType name="textSpell" class="solr.TextField" positionIncrementGap="100" >
|
|
357
|
+
<analyzer>
|
|
358
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
359
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
|
|
360
|
+
<filter class="solr.StandardFilterFactory"/>
|
|
361
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
|
362
|
+
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
363
|
+
</analyzer>
|
|
364
|
+
</fieldType>
|
|
365
|
+
|
|
366
|
+
<!-- charFilter + WhitespaceTokenizer -->
|
|
367
|
+
<!--
|
|
368
|
+
<fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
|
|
369
|
+
<analyzer>
|
|
370
|
+
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
|
|
371
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
372
|
+
</analyzer>
|
|
373
|
+
</fieldType>
|
|
374
|
+
-->
|
|
375
|
+
|
|
376
|
+
<!-- This is an example of using the KeywordTokenizer along
|
|
377
|
+
With various TokenFilterFactories to produce a sortable field
|
|
378
|
+
that does not include some properties of the source text
|
|
379
|
+
-->
|
|
380
|
+
<fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
|
|
381
|
+
<analyzer>
|
|
382
|
+
<!-- KeywordTokenizer does no actual tokenizing, so the entire
|
|
383
|
+
input string is preserved as a single token
|
|
384
|
+
-->
|
|
385
|
+
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
|
386
|
+
<!-- The LowerCase TokenFilter does what you expect, which can be
|
|
387
|
+
when you want your sorting to be case insensitive
|
|
388
|
+
-->
|
|
389
|
+
<filter class="solr.LowerCaseFilterFactory" />
|
|
390
|
+
<!-- The TrimFilter removes any leading or trailing whitespace -->
|
|
391
|
+
<filter class="solr.TrimFilterFactory" />
|
|
392
|
+
<!-- The PatternReplaceFilter gives you the flexibility to use
|
|
393
|
+
Java Regular expression to replace any sequence of characters
|
|
394
|
+
matching a pattern with an arbitrary replacement string,
|
|
395
|
+
which may include back references to portions of the original
|
|
396
|
+
string matched by the pattern.
|
|
397
|
+
|
|
398
|
+
See the Java Regular Expression documentation for more
|
|
399
|
+
information on pattern and replacement string syntax.
|
|
400
|
+
|
|
401
|
+
http://java.sun.com/j2se/1.5.0/docs/api/java/util/regex/package-summary.html
|
|
402
|
+
-->
|
|
403
|
+
<filter class="solr.PatternReplaceFilterFactory"
|
|
404
|
+
pattern="([^a-z])" replacement="" replace="all"
|
|
405
|
+
/>
|
|
406
|
+
</analyzer>
|
|
407
|
+
</fieldType>
|
|
408
|
+
|
|
409
|
+
<fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
|
|
410
|
+
<analyzer>
|
|
411
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
412
|
+
<filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
|
|
413
|
+
</analyzer>
|
|
414
|
+
</fieldtype>
|
|
415
|
+
|
|
416
|
+
<fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
|
|
417
|
+
<analyzer>
|
|
418
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
419
|
+
<!--
|
|
420
|
+
The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
|
|
421
|
+
a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
|
|
422
|
+
Attributes of the DelimitedPayloadTokenFilterFactory :
|
|
423
|
+
"delimiter" - a one character delimiter. Default is | (pipe)
|
|
424
|
+
"encoder" - how to encode the following value into a playload
|
|
425
|
+
float -> org.apache.lucene.analysis.payloads.FloatEncoder,
|
|
426
|
+
integer -> o.a.l.a.p.IntegerEncoder
|
|
427
|
+
identity -> o.a.l.a.p.IdentityEncoder
|
|
428
|
+
Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
|
|
429
|
+
-->
|
|
430
|
+
<filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
|
|
431
|
+
</analyzer>
|
|
432
|
+
</fieldtype>
|
|
433
|
+
|
|
434
|
+
<!-- lowercases the entire field value, keeping it as a single token. -->
|
|
435
|
+
<fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
|
|
436
|
+
<analyzer>
|
|
437
|
+
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
|
438
|
+
<filter class="solr.LowerCaseFilterFactory" />
|
|
439
|
+
</analyzer>
|
|
440
|
+
</fieldType>
|
|
441
|
+
|
|
442
|
+
<fieldType name="text_path" class="solr.TextField" positionIncrementGap="100">
|
|
443
|
+
<analyzer>
|
|
444
|
+
<tokenizer class="solr.PathHierarchyTokenizerFactory"/>
|
|
445
|
+
</analyzer>
|
|
446
|
+
</fieldType>
|
|
447
|
+
|
|
448
|
+
<!-- since fields of this type are by default not stored or indexed,
|
|
449
|
+
any data added to them will be ignored outright. -->
|
|
450
|
+
<fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
|
|
451
|
+
|
|
452
|
+
<!-- This point type indexes the coordinates as separate fields (subFields)
|
|
453
|
+
If subFieldType is defined, it references a type, and a dynamic field
|
|
454
|
+
definition is created matching *___<typename>. Alternately, if
|
|
455
|
+
subFieldSuffix is defined, that is used to create the subFields.
|
|
456
|
+
Example: if subFieldType="double", then the coordinates would be
|
|
457
|
+
indexed in fields myloc_0___double,myloc_1___double.
|
|
458
|
+
Example: if subFieldSuffix="_d" then the coordinates would be indexed
|
|
459
|
+
in fields myloc_0_d,myloc_1_d
|
|
460
|
+
The subFields are an implementation detail of the fieldType, and end
|
|
461
|
+
users normally should not need to know about them.
|
|
462
|
+
-->
|
|
463
|
+
<fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
|
|
464
|
+
|
|
465
|
+
<!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
|
|
466
|
+
<fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
|
|
467
|
+
|
|
468
|
+
<!--
|
|
469
|
+
A Geohash is a compact representation of a latitude longitude pair in a single field.
|
|
470
|
+
See http://wiki.apache.org/solr/SpatialSearch
|
|
471
|
+
-->
|
|
472
|
+
<fieldtype name="geohash" class="solr.GeoHashField"/>
|
|
473
|
+
</types>
|
|
474
|
+
|
|
475
|
+
|
|
476
|
+
<fields>
|
|
477
|
+
<!-- Valid attributes for fields:
|
|
478
|
+
name: mandatory - the name for the field
|
|
479
|
+
type: mandatory - the name of a previously defined type from the
|
|
480
|
+
<types> section
|
|
481
|
+
indexed: true if this field should be indexed (searchable or sortable)
|
|
482
|
+
stored: true if this field should be retrievable
|
|
483
|
+
multiValued: true if this field may contain multiple values per document
|
|
484
|
+
omitNorms: (expert) set to true to omit the norms associated with
|
|
485
|
+
this field (this disables length normalization and index-time
|
|
486
|
+
boosting for the field, and saves some memory). Only full-text
|
|
487
|
+
fields or fields that need an index-time boost need norms.
|
|
488
|
+
termVectors: [false] set to true to store the term vector for a
|
|
489
|
+
given field.
|
|
490
|
+
When using MoreLikeThis, fields used for similarity should be
|
|
491
|
+
stored for best performance.
|
|
492
|
+
termPositions: Store position information with the term vector.
|
|
493
|
+
This will increase storage costs.
|
|
494
|
+
termOffsets: Store offset information with the term vector. This
|
|
495
|
+
will increase storage costs.
|
|
496
|
+
default: a value that should be used if no value is specified
|
|
497
|
+
when adding a document.
|
|
498
|
+
-->
|
|
499
|
+
|
|
500
|
+
<field name="id" type="string" indexed="true" stored="true" required="true" />
|
|
501
|
+
<field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false" />
|
|
502
|
+
|
|
503
|
+
<!-- default, catch all search field -->
|
|
504
|
+
<!-- set multiValued to true in order to copyfield -->
|
|
505
|
+
<field name="text" type="text" indexed="true" stored="false" multiValued="true" />
|
|
506
|
+
|
|
507
|
+
<field name="type" type="string" indexed="false" stored="false" multiValued="true" />
|
|
508
|
+
|
|
509
|
+
<field name="dataProvider_id" type="string" indexed="true" stored="true" multiValued="true" />
|
|
510
|
+
<field name="dataProvider_type" type="string" indexed="false" stored="false" multiValued="true" />
|
|
511
|
+
<field name="dataProvider_name" type="string" indexed="true" stored="true" multiValued="true" />
|
|
512
|
+
<field name="dataProvider_providedLabel" type="string" indexed="true" stored="true" multiValued="true" />
|
|
513
|
+
|
|
514
|
+
<field name="hasView_id" type="string" indexed="true" stored="true" multiValued="true" />
|
|
515
|
+
<field name="hasView_type" type="string" indexed="false" stored="false" multiValued="true" />
|
|
516
|
+
<field name="hasView_format" type="string" indexed="true" stored="true" multiValued="true" />
|
|
517
|
+
<field name="hasView_rights" type="string" indexed="true" stored="true" multiValued="true" />
|
|
518
|
+
<field name="hasView_rightsStatement_id" type="string" indexed="true" stored="true" multiValued="true" />
|
|
519
|
+
|
|
520
|
+
<field name="intermediateProvider_id" type="string" indexed="true" stored="true" multiValued="true" />
|
|
521
|
+
<field name="intermediateProvider_type" type="string" indexed="false" stored="false" multiValued="true" />
|
|
522
|
+
<field name="intermediateProvider_name" type="string" indexed="true" stored="true" multiValued="true" />
|
|
523
|
+
<field name="intermediateProvider_providedLabel" type="string" indexed="true" stored="true" multiValued="true" />
|
|
524
|
+
|
|
525
|
+
<field name="isShownAt_id" type="string" indexed="true" stored="true" multiValued="true" />
|
|
526
|
+
<field name="isShownAt_type" type="string" indexed="false" stored="false" multiValued="true" />
|
|
527
|
+
<field name="isShownAt_format" type="string" indexed="true" stored="true" multiValued="true" />
|
|
528
|
+
<field name="isShownAt_rights" type="string" indexed="true" stored="true" multiValued="true" />
|
|
529
|
+
<field name="isShownAt_rightsStatement_id" type="string" indexed="true" stored="true" multiValued="true" />
|
|
530
|
+
|
|
531
|
+
<field name="object_id" type="string" indexed="true" stored="true" multiValued="true" />
|
|
532
|
+
<field name="object_type" type="string" indexed="false" stored="false" multiValued="true" />
|
|
533
|
+
<field name="object_format" type="string" indexed="true" stored="true" multiValued="true" />
|
|
534
|
+
<field name="object_rights" type="string" indexed="true" stored="true" multiValued="true" />
|
|
535
|
+
<field name="object_rightsStatement_id" type="string" indexed="true" stored="true" multiValued="true" />
|
|
536
|
+
|
|
537
|
+
<field name="originalRecord" type="string" indexed="true" stored="true" multiValued="true" />
|
|
538
|
+
|
|
539
|
+
<field name="preview_id" type="string" indexed="true" stored="true" multiValued="true" />
|
|
540
|
+
<field name="preview_type" type="string" indexed="false" stored="false" multiValued="true" />
|
|
541
|
+
<field name="preview_format" type="string" indexed="true" stored="true" multiValued="true" />
|
|
542
|
+
<field name="preview_rights" type="string" indexed="true" stored="true" multiValued="true" />
|
|
543
|
+
<field name="preview_rightsStatement_id" type="string" indexed="true" stored="true" multiValued="true" />
|
|
544
|
+
|
|
545
|
+
<field name="provider_id" type="string" indexed="true" stored="true" multiValued="true" />
|
|
546
|
+
<field name="provider_type" type="string" indexed="false" stored="false" multiValued="true" />
|
|
547
|
+
<field name="provider_name" type="string" indexed="true" stored="true" multiValued="true" />
|
|
548
|
+
<field name="provider_providedLabel" type="string" indexed="true" stored="true" multiValued="true" />
|
|
549
|
+
|
|
550
|
+
<field name="rightsStatement_id" type="string" indexed="true" stored="true" multiValued="true" />
|
|
551
|
+
|
|
552
|
+
<field name="sourceResource_id" type="string" indexed="true" stored="true" multiValued="true"/>
|
|
553
|
+
<field name="sourceResource_type" type="string" indexed="false" stored="false" multiValued="true" />
|
|
554
|
+
<field name="sourceResource_alternative" type="string" indexed="true" stored="true" multiValued="true" />
|
|
555
|
+
|
|
556
|
+
<field name="sourceResource_collection_id" type="string" indexed="true" stored="true" multiValued="true" />
|
|
557
|
+
<field name="sourceResource_collection_type" type="string" indexed="false" stored="false" multiValued="true" />
|
|
558
|
+
<field name="sourceResource_collection_providedLabel" type="string" indexed="true" stored="true" multiValued="true" />
|
|
559
|
+
<field name="sourceResource_collection_title" type="string" indexed="true" stored="true" multiValued="true" />
|
|
560
|
+
<field name="sourceResource_collection_description" type="text" indexed="true" stored="true" multiValued="true" />
|
|
561
|
+
|
|
562
|
+
<field name="sourceResource_contributor_id" type="string" indexed="true" stored="true" multiValued="true" />
|
|
563
|
+
<field name="sourceResource_contributor_type" type="string" indexed="false" stored="false" multiValued="true" />
|
|
564
|
+
<field name="sourceResource_contributor_name" type="string" indexed="true" stored="true" multiValued="true" />
|
|
565
|
+
<field name="sourceResource_contributor_providedLabel" type="string" indexed="true" stored="true" multiValued="true" />
|
|
566
|
+
|
|
567
|
+
<field name="sourceResource_creator_id" type="string" indexed="true" stored="true" multiValued="true" />
|
|
568
|
+
<field name="sourceResource_creator_type" type="string" indexed="false" stored="false" multiValued="true" />
|
|
569
|
+
<field name="sourceResource_creator_name" type="string" indexed="true" stored="true" multiValued="true" />
|
|
570
|
+
<field name="sourceResource_creator_providedLabel" type="string" indexed="true" stored="true" multiValued="true" />
|
|
571
|
+
|
|
572
|
+
<!-- TODO: Change date_begin and date_end type to "date" assuming they have been correctly formatted -->
|
|
573
|
+
<field name="sourceResource_date_id" type="string" indexed="true" stored="true" multiValued="true" />
|
|
574
|
+
<field name="sourceResource_date_type" type="string" indexed="false" stored="false" multiValued="true" />
|
|
575
|
+
<field name="sourceResource_date_begin" type="string" indexed="true" stored="true" multiValued="true" />
|
|
576
|
+
<field name="sourceResource_date_end" type="string" indexed="true" stored="true" multiValued="true" />
|
|
577
|
+
<field name="sourceResource_date_providedLabel" type="string" indexed="true" stored="true" multiValued="true" />
|
|
578
|
+
|
|
579
|
+
<field name="sourceResource_description" type="text" indexed="true" stored="true" multiValued="true" />
|
|
580
|
+
<field name="sourceResource_extent" type="string" indexed="true" stored="true" multiValued="true" />
|
|
581
|
+
<field name="sourceResource_format" type="string" indexed="true" stored="true" multiValued="true" />
|
|
582
|
+
<field name="sourceResource_identifier" type="string" indexed="true" stored="true" multiValued="true" />
|
|
583
|
+
|
|
584
|
+
<field name="sourceResource_language_id" type="string" indexed="true" stored="true" multiValued="true" />
|
|
585
|
+
<field name="sourceResource_language_providedLabel" type="string" indexed="true" stored="true" multiValued="true" />
|
|
586
|
+
<field name="sourceResource_language_type" type="string" indexed="true" stored="true" multiValued="true" />
|
|
587
|
+
|
|
588
|
+
<field name="sourceResource_genre" type="string" indexed="true" stored="true" multiValued="true" />
|
|
589
|
+
<field name="sourceResource_genre_id" type="string" indexed="true" stored="true" multiValued="true" />
|
|
590
|
+
<field name="sourceResource_genre_providedLabel" type="string" indexed="true" stored="true" multiValued="true" />
|
|
591
|
+
<field name="sourceResource_genre_type" type="string" indexed="true" stored="true" multiValued="true" />
|
|
592
|
+
|
|
593
|
+
<field name="sourceResource_publisher_id" type="string" indexed="true" stored="true" multiValued="true" />
|
|
594
|
+
<field name="sourceResource_publisher_type" type="string" indexed="false" stored="false" multiValued="true" />
|
|
595
|
+
<field name="sourceResource_publisher_name" type="string" indexed="true" stored="true" multiValued="true" />
|
|
596
|
+
<field name="sourceResource_publisher_providedLabel" type="string" indexed="true" stored="true" multiValued="true" />
|
|
597
|
+
|
|
598
|
+
<field name="sourceResource_relation" type="string" indexed="true" stored="true" multiValued="true" />
|
|
599
|
+
<field name="sourceResource_isReplacedBy" type="string" indexed="true" stored="true" multiValued="true" />
|
|
600
|
+
<field name="sourceResource_replaces" type="string" indexed="true" stored="true" multiValued="true" />
|
|
601
|
+
<field name="sourceResource_rights" type="string" indexed="true" stored="true" multiValued="true" />
|
|
602
|
+
<field name="sourceResource_rightsHolder" type="string" indexed="true" stored="true" multiValued="true" />
|
|
603
|
+
|
|
604
|
+
<field name="sourceResource_rightsHolder_id" type="string" indexed="true" stored="true" multiValued="true" />
|
|
605
|
+
<field name="sourceResource_rightsHolder_type" type="string" indexed="false" stored="false" multiValued="true" />
|
|
606
|
+
<field name="sourceResource_rightsHolder_name" type="string" indexed="true" stored="true" multiValued="true" />
|
|
607
|
+
<field name="sourceResource_rightsHolder_providedLabel" type="string" indexed="true" stored="true" multiValued="true" />
|
|
608
|
+
|
|
609
|
+
<field name="sourceResource_spatial_id" type="string" indexed="true" stored="true" multiValued="true" />
|
|
610
|
+
<field name="sourceResource_spatial_type" type="string" indexed="false" stored="false" multiValued="true" />
|
|
611
|
+
<field name="sourceResource_spatial_exactMatch" type="string" indexed="true" stored="true" multiValued="true" />
|
|
612
|
+
<field name="sourceResource_spatial_countryCode" type="string" indexed="true" stored="true" multiValued="true" />
|
|
613
|
+
<field name="sourceResource_spatial_parentFeature_id" type="string" indexed="true" stored="true" multiValued="true" />
|
|
614
|
+
<field name="sourceResource_spatial_alt" type="string" indexed="true" stored="true" multiValued="true" />
|
|
615
|
+
<field name="sourceResource_spatial_lat" type="string" indexed="true" stored="true" multiValued="true" />
|
|
616
|
+
<field name="sourceResource_spatial_long" type="string" indexed="true" stored="true" multiValued="true" />
|
|
617
|
+
<field name="sourceResource_spatial_name" type="string" indexed="true" stored="true" multiValued="true" />
|
|
618
|
+
<field name="sourceResource_spatial_providedLabel" type="string" indexed="true" stored="true" multiValued="true" />
|
|
619
|
+
|
|
620
|
+
<field name="sourceResource_specType_id" type="string" indexed="true" stored="true" multiValued="true" />
|
|
621
|
+
<field name="sourceResource_specType_type" type="string" indexed="false" stored="false" multiValued="true" />
|
|
622
|
+
|
|
623
|
+
<field name="sourceResource_subject_id" type="string" indexed="true" stored="true" multiValued="true" />
|
|
624
|
+
<field name="sourceResource_subject_type" type="string" indexed="false" stored="false" multiValued="true" />
|
|
625
|
+
<field name="sourceResource_subject_name" type="string" indexed="true" stored="true" multiValued="true" />
|
|
626
|
+
<field name="sourceResource_subject_providedLabel" type="string" indexed="true" stored="true" multiValued="true" />
|
|
627
|
+
|
|
628
|
+
<field name="sourceResource_temporal" type="string" indexed="true" stored="true" multiValued="true" />
|
|
629
|
+
<field name="sourceResource_title" type="string" indexed="true" stored="true" multiValued="true" />
|
|
630
|
+
|
|
631
|
+
<field name="sourceResource_type_id" type="string" indexed="true" stored="true" multiValued="true" />
|
|
632
|
+
<field name="sourceResource_type_type" type="string" indexed="false" stored="false" multiValued="true" />
|
|
633
|
+
<field name="sourceResource_type_providedLabel" type="string" indexed="true" stored="true" multiValued="true" />
|
|
634
|
+
<field name="sourceResource_type_name" type="string" indexed="true" stored="true" multiValued="true" />
|
|
635
|
+
|
|
636
|
+
<!-- Dynamic field definitions. If a field name is not found, dynamicFields
|
|
637
|
+
will be used if the name matches any of the patterns.
|
|
638
|
+
RESTRICTION: the glob-like pattern in the name attribute must have
|
|
639
|
+
a "*" only at the start or the end.
|
|
640
|
+
EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
|
|
641
|
+
Longer patterns will be matched first. if equal size patterns
|
|
642
|
+
both match, the first appearing in the schema will be used. -->
|
|
643
|
+
<dynamicField name="*_i" type="int" indexed="true" stored="true"/>
|
|
644
|
+
<dynamicField name="*_s" type="string" indexed="true" stored="true"/>
|
|
645
|
+
<dynamicField name="*_l" type="long" indexed="true" stored="true"/>
|
|
646
|
+
<dynamicField name="*_t" type="text" indexed="true" stored="true" multiValued="true"/>
|
|
647
|
+
<dynamicField name="*_txt" type="text_general" indexed="true" stored="true" multiValued="true"/>
|
|
648
|
+
<dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
|
|
649
|
+
<dynamicField name="*_f" type="float" indexed="true" stored="true"/>
|
|
650
|
+
<dynamicField name="*_d" type="double" indexed="true" stored="true"/>
|
|
651
|
+
|
|
652
|
+
<!-- Type used to index the lat and lon components for the "location" FieldType -->
|
|
653
|
+
<dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false"/>
|
|
654
|
+
|
|
655
|
+
<dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
|
|
656
|
+
<dynamicField name="*_p" type="location" indexed="true" stored="true"/>
|
|
657
|
+
|
|
658
|
+
<!-- some trie-coded dynamic fields for faster range queries -->
|
|
659
|
+
<dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
|
|
660
|
+
<dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
|
|
661
|
+
<dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
|
|
662
|
+
<dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
|
|
663
|
+
<dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
|
|
664
|
+
|
|
665
|
+
<dynamicField name="*_pi" type="pint" indexed="true" stored="true"/>
|
|
666
|
+
|
|
667
|
+
<dynamicField name="ignored_*" type="ignored" multiValued="true"/>
|
|
668
|
+
<dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
|
|
669
|
+
|
|
670
|
+
<dynamicField name="random_*" type="random" />
|
|
671
|
+
|
|
672
|
+
<dynamicField name="*_display" type="string" indexed="false" stored="true" multiValued="true" />
|
|
673
|
+
<dynamicField name="*_facet" type="string" indexed="true" stored="false" multiValued="true" />
|
|
674
|
+
<dynamicField name="*_sort" type="alphaOnlySort" indexed="true" stored="false" multiValued="false" />
|
|
675
|
+
<dynamicField name="*_unstem_search" type="text_general" indexed="true" stored="false" multiValued="true" />
|
|
676
|
+
<dynamicField name="*spell" type="textSpell" indexed="true" stored="false" multiValued="true" />
|
|
677
|
+
|
|
678
|
+
<!-- uncomment the following to ignore any fields that don't already match an existing
|
|
679
|
+
field name or dynamic field, rather than reporting them as an error.
|
|
680
|
+
alternately, change the type="ignored" to some other type e.g. "text" if you want
|
|
681
|
+
unknown fields indexed and/or stored by default -->
|
|
682
|
+
<!--dynamicField name="*" type="ignored" multiValued="true" /-->
|
|
683
|
+
|
|
684
|
+
</fields>
|
|
685
|
+
|
|
686
|
+
<!-- Field to use to determine and enforce document uniqueness.
|
|
687
|
+
Unless this field is marked with required="false", it will be a required field
|
|
688
|
+
-->
|
|
689
|
+
<uniqueKey>id</uniqueKey>
|
|
690
|
+
|
|
691
|
+
<!-- field for the QueryParser to use when an explicit fieldname is absent -->
|
|
692
|
+
<defaultSearchField>text</defaultSearchField>
|
|
693
|
+
|
|
694
|
+
<!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
|
|
695
|
+
<solrQueryParser defaultOperator="AND" />
|
|
696
|
+
|
|
697
|
+
<!-- copyField commands copy one field to another at the time a document
|
|
698
|
+
is added to the index. It's used either to index the same field differently,
|
|
699
|
+
or to add multiple fields to the same field for easier/faster searching. -->
|
|
700
|
+
<!-- Copy Fields -->
|
|
701
|
+
<!-- The source fields are copied into the text field to allow tokenization -->
|
|
702
|
+
<copyField source="dataProvider_name" dest="text" />
|
|
703
|
+
<copyField source="dataProvider_providedLabel" dest="text" />
|
|
704
|
+
<copyField source="hasView_format" dest="text" />
|
|
705
|
+
<copyField source="hasView_rights" dest="text" />
|
|
706
|
+
<copyField source="intermediateProvider_name" dest="text" />
|
|
707
|
+
<copyField source="intermediateProvider_providedLabel" dest="text" />
|
|
708
|
+
<copyField source="isShownAt_format" dest="text" />
|
|
709
|
+
<copyField source="isShownAt_rights" dest="text" />
|
|
710
|
+
<copyField source="object_format" dest="text" />
|
|
711
|
+
<copyField source="object_rights" dest="text" />
|
|
712
|
+
<copyField source="preview_format" dest="text" />
|
|
713
|
+
<copyField source="preview_rights" dest="text" />
|
|
714
|
+
<copyField source="provider_name" dest="text" />
|
|
715
|
+
<copyField source="provider_providedLabel" dest="text" />
|
|
716
|
+
<copyField source="sourceResource_alternative" dest="text" />
|
|
717
|
+
<copyField source="sourceResource_collection_providedLabel" dest="text" />
|
|
718
|
+
<copyField source="sourceResource_collection_title" dest="text" />
|
|
719
|
+
<copyField source="sourceResource_contributor_name" dest="text" />
|
|
720
|
+
<copyField source="sourceResource_contributor_providedLabel" dest="text" />
|
|
721
|
+
<copyField source="sourceResource_creator_name" dest="text" />
|
|
722
|
+
<copyField source="sourceResource_creator_providedLabel" dest="text" />
|
|
723
|
+
<copyField source="sourceResource_date_providedLabel" dest="text" />
|
|
724
|
+
<copyField source="sourceResource_extent" dest="text" />
|
|
725
|
+
<copyField source="sourceResource_format" dest="text" />
|
|
726
|
+
<copyField source="sourceResource_genre" dest="text" />
|
|
727
|
+
<copyField source="sourceResource_publisher_name" dest="text" />
|
|
728
|
+
<copyField source="sourceResource_publisher_providedLabel" dest="text" />
|
|
729
|
+
<copyField source="sourceResource_relation" dest="text" />
|
|
730
|
+
<copyField source="sourceResource_isReplacedBy" dest="text" />
|
|
731
|
+
<copyField source="sourceResource_replaces" dest="text" />
|
|
732
|
+
<copyField source="sourceResource_rights" dest="text" />
|
|
733
|
+
<copyField source="sourceResource_spatial_name" dest="text" />
|
|
734
|
+
<copyField source="sourceResource_spatial_providedLabel" dest="text" />
|
|
735
|
+
<copyField source="sourceResource_subject_name" dest="text" />
|
|
736
|
+
<copyField source="sourceResource_subject_providedLabel" dest="text" />
|
|
737
|
+
<copyField source="sourceResource_temporal" dest="text" />
|
|
738
|
+
<copyField source="sourceResource_title" dest="text" />
|
|
739
|
+
<copyField source="sourceResource_type_name" dest="text" />
|
|
740
|
+
|
|
741
|
+
<!-- Above, multiple source fields are copied to the [text] field.
|
|
742
|
+
Another way to map multiple source fields to the same
|
|
743
|
+
destination field is to use the dynamic field syntax.
|
|
744
|
+
copyField also supports a maxChars to copy setting. -->
|
|
745
|
+
|
|
746
|
+
<!-- <copyField source="*_t" dest="text" maxChars="3000"/> -->
|
|
747
|
+
|
|
748
|
+
<!-- copy name to alphaNameSort, a field designed for sorting by name -->
|
|
749
|
+
<!-- <copyField source="name" dest="alphaNameSort"/> -->
|
|
750
|
+
|
|
751
|
+
|
|
752
|
+
<!-- Similarity is the scoring routine for each document vs. a query.
|
|
753
|
+
A custom similarity may be specified here, but the default is fine
|
|
754
|
+
for most applications. -->
|
|
755
|
+
<!-- <similarity class="org.apache.lucene.search.DefaultSimilarity"/> -->
|
|
756
|
+
<!-- ... OR ...
|
|
757
|
+
Specify a SimilarityFactory class name implementation
|
|
758
|
+
allowing parameters to be used.
|
|
759
|
+
-->
|
|
760
|
+
<!--
|
|
761
|
+
<similarity class="com.example.solr.CustomSimilarityFactory">
|
|
762
|
+
<str name="paramkey">param value</str>
|
|
763
|
+
</similarity>
|
|
764
|
+
-->
|
|
765
|
+
|
|
766
|
+
|
|
767
|
+
</schema>
|
|
@@ -0,0 +1,160 @@
|
|
|
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 a stripped down config file used for a simple example...
|
|
21
|
+
It is *not* a good example to work from.
|
|
22
|
+
-->
|
|
23
|
+
<config>
|
|
24
|
+
<luceneMatchVersion>LUCENE_40</luceneMatchVersion>
|
|
25
|
+
<!-- The DirectoryFactory to use for indexes.
|
|
26
|
+
solr.StandardDirectoryFactory, the default, is filesystem based.
|
|
27
|
+
solr.RAMDirectoryFactory is memory based, not persistent, and doesn't work with replication. -->
|
|
28
|
+
<directoryFactory name="DirectoryFactory" class="${solr.directoryFactory:solr.StandardDirectoryFactory}"/>
|
|
29
|
+
|
|
30
|
+
<lib dir="../lib/contrib/analysis-extras/lib" />
|
|
31
|
+
<lib dir="../lib/contrib/analysis-extras/lucene-libs" />
|
|
32
|
+
|
|
33
|
+
<dataDir>${solr.blacklight-core.data.dir:}</dataDir>
|
|
34
|
+
|
|
35
|
+
<requestHandler name="/replication" class="solr.ReplicationHandler" startup="lazy" />
|
|
36
|
+
|
|
37
|
+
<requestDispatcher handleSelect="true" >
|
|
38
|
+
<requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="2048" />
|
|
39
|
+
</requestDispatcher>
|
|
40
|
+
|
|
41
|
+
<requestHandler name="standard" class="solr.StandardRequestHandler" />
|
|
42
|
+
<requestHandler name="/analysis/field" startup="lazy" class="solr.FieldAnalysisRequestHandler" />
|
|
43
|
+
<requestHandler name="/update" class="solr.UpdateRequestHandler" />
|
|
44
|
+
<requestHandler name="/admin/" class="org.apache.solr.handler.admin.AdminHandlers" />
|
|
45
|
+
|
|
46
|
+
<requestHandler name="/admin/ping" class="solr.PingRequestHandler">
|
|
47
|
+
<lst name="invariants">
|
|
48
|
+
<str name="q">solrpingquery</str>
|
|
49
|
+
</lst>
|
|
50
|
+
<lst name="defaults">
|
|
51
|
+
<str name="echoParams">all</str>
|
|
52
|
+
</lst>
|
|
53
|
+
</requestHandler>
|
|
54
|
+
|
|
55
|
+
<!-- config for the admin interface -->
|
|
56
|
+
<admin>
|
|
57
|
+
<defaultQuery>solr</defaultQuery>
|
|
58
|
+
</admin>
|
|
59
|
+
|
|
60
|
+
<!-- SearchHandler
|
|
61
|
+
|
|
62
|
+
http://wiki.apache.org/solr/SearchHandler
|
|
63
|
+
|
|
64
|
+
For processing Search Queries, the primary Request Handler
|
|
65
|
+
provided with Solr is "SearchHandler" It delegates to a sequent
|
|
66
|
+
of SearchComponents (see below) and supports distributed
|
|
67
|
+
queries across multiple shards
|
|
68
|
+
-->
|
|
69
|
+
<requestHandler name="search" class="solr.SearchHandler" default="true">
|
|
70
|
+
<!-- default values for query parameters can be specified, these
|
|
71
|
+
will be overridden by parameters in the request
|
|
72
|
+
-->
|
|
73
|
+
<lst name="defaults">
|
|
74
|
+
<str name="defType">dismax</str>
|
|
75
|
+
<str name="echoParams">explicit</str>
|
|
76
|
+
<int name="rows">10</int>
|
|
77
|
+
|
|
78
|
+
<str name="q.alt">*:*</str>
|
|
79
|
+
<str name="mm">2<-1 5<-2 6<90%</str>
|
|
80
|
+
|
|
81
|
+
<!-- TODO: Configure qf and pf for better search results -->
|
|
82
|
+
|
|
83
|
+
<!-- this qf and pf are used by default, if not otherwise specified by
|
|
84
|
+
client. The default blacklight_config will use these for the
|
|
85
|
+
"keywords" search. See the author_qf/author_pf, title_qf, etc
|
|
86
|
+
below, which the default blacklight_config will specify for
|
|
87
|
+
those searches. You may also be interested in:
|
|
88
|
+
http://wiki.apache.org/solr/LocalParams
|
|
89
|
+
-->
|
|
90
|
+
|
|
91
|
+
<str name="qf">
|
|
92
|
+
dataProvider_providedLabel
|
|
93
|
+
sourceResource_collection_title
|
|
94
|
+
sourceResource_creator_providedLabel
|
|
95
|
+
sourceResource_date_providedLabel
|
|
96
|
+
sourceResource_description
|
|
97
|
+
sourceResource_format
|
|
98
|
+
sourceResource_rights
|
|
99
|
+
sourceResource_spatial_providedLabel
|
|
100
|
+
sourceResource_subject_providedLabel
|
|
101
|
+
sourceResource_title
|
|
102
|
+
sourceResource_type_name
|
|
103
|
+
text
|
|
104
|
+
</str>
|
|
105
|
+
|
|
106
|
+
<str name="pf">
|
|
107
|
+
dataProvider_providedLabel
|
|
108
|
+
sourceResource_collection_title
|
|
109
|
+
sourceResource_creator_providedLabel
|
|
110
|
+
sourceResource_date_providedLabel
|
|
111
|
+
sourceResource_description
|
|
112
|
+
sourceResource_format
|
|
113
|
+
sourceResource_rights
|
|
114
|
+
sourceResource_spatial_providedLabel
|
|
115
|
+
sourceResource_subject_providedLabel
|
|
116
|
+
sourceResource_title
|
|
117
|
+
sourceResource_type_name
|
|
118
|
+
text
|
|
119
|
+
</str>
|
|
120
|
+
|
|
121
|
+
<int name="ps">3</int>
|
|
122
|
+
<float name="tie">0.01</float>
|
|
123
|
+
|
|
124
|
+
<str name="fl">
|
|
125
|
+
id,
|
|
126
|
+
dataProvider_providedLabel,
|
|
127
|
+
preview_id,
|
|
128
|
+
sourceResource_collection_title,
|
|
129
|
+
sourceResource_creator_providedLabel,
|
|
130
|
+
sourceResource_date_providedLabel,
|
|
131
|
+
sourceResource_description,
|
|
132
|
+
sourceResource_format,
|
|
133
|
+
sourceResource_rights,
|
|
134
|
+
sourceResource_spatial_providedLabel,
|
|
135
|
+
sourceResource_subject_providedLabel,
|
|
136
|
+
sourceResource_title,
|
|
137
|
+
sourceResource_type_name
|
|
138
|
+
</str>
|
|
139
|
+
|
|
140
|
+
<str name="facet">true</str>
|
|
141
|
+
<str name="facet.mincount">1</str>
|
|
142
|
+
<str name="facet.limit">10</str>
|
|
143
|
+
<str name="facet.field">dataProvider_providedLabel</str>
|
|
144
|
+
|
|
145
|
+
</lst>
|
|
146
|
+
|
|
147
|
+
</requestHandler>
|
|
148
|
+
|
|
149
|
+
<!-- for requests to get a single document; use id=666 instead of q=id:666 -->
|
|
150
|
+
<requestHandler name="document" class="solr.SearchHandler" >
|
|
151
|
+
<lst name="defaults">
|
|
152
|
+
<str name="echoParams">all</str>
|
|
153
|
+
<str name="fl">*</str>
|
|
154
|
+
<str name="rows">1</str>
|
|
155
|
+
<str name="q">{!raw f=id v=$id}</str> <!-- use id=666 instead of q=id:666 -->
|
|
156
|
+
</lst>
|
|
157
|
+
</requestHandler>
|
|
158
|
+
|
|
159
|
+
</config>
|
|
160
|
+
|
|
@@ -92,23 +92,28 @@ module Krikri
|
|
|
92
92
|
##
|
|
93
93
|
# @yield [Faraday::Response] the response returned for the request
|
|
94
94
|
def with_response
|
|
95
|
-
|
|
96
|
-
|
|
97
|
-
|
|
98
|
-
|
|
99
|
-
|
|
100
|
-
|
|
101
|
-
|
|
102
|
-
|
|
103
|
-
|
|
104
|
-
|
|
105
|
-
|
|
106
|
-
|
|
107
|
-
|
|
108
|
-
|
|
95
|
+
begin
|
|
96
|
+
response = @request_thread.value
|
|
97
|
+
rescue => e
|
|
98
|
+
if inline_exceptions?
|
|
99
|
+
# Deliver an error response to the caller to allow uniform access
|
|
100
|
+
msg = e.message + "\n\n" + e.backtrace.join("\n")
|
|
101
|
+
response = Faraday::Response.new(status: 500,
|
|
102
|
+
body: msg,
|
|
103
|
+
response_headers: {
|
|
104
|
+
'X-Exception' => e,
|
|
105
|
+
'X-Exception-Message' => e.message,
|
|
106
|
+
'X-Internal-Response' => 'true'
|
|
107
|
+
})
|
|
108
|
+
else
|
|
109
|
+
raise e
|
|
110
|
+
end
|
|
109
111
|
end
|
|
112
|
+
|
|
113
|
+
yield response
|
|
110
114
|
end
|
|
111
115
|
|
|
116
|
+
|
|
112
117
|
private
|
|
113
118
|
|
|
114
119
|
##
|
data/lib/krikri/version.rb
CHANGED
|
@@ -127,4 +127,15 @@ describe Krikri::AsyncUriGetter do
|
|
|
127
127
|
end
|
|
128
128
|
end
|
|
129
129
|
end
|
|
130
|
+
|
|
131
|
+
context 'inline exceptions' do
|
|
132
|
+
subject { described_class.new(opts: { inline_exceptions: true }) }
|
|
133
|
+
|
|
134
|
+
it 'does not interfere with exceptions thrown by with_response' do
|
|
135
|
+
r = subject.add_request(uri: test_uri)
|
|
136
|
+
expect do
|
|
137
|
+
r.with_response { |_| raise "Programming error!" }
|
|
138
|
+
end.to raise_error
|
|
139
|
+
end
|
|
140
|
+
end
|
|
130
141
|
end
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: krikri
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.12.
|
|
4
|
+
version: 0.12.3
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Audrey Altman
|
|
@@ -11,7 +11,7 @@ authors:
|
|
|
11
11
|
autorequire:
|
|
12
12
|
bindir: bin
|
|
13
13
|
cert_chain: []
|
|
14
|
-
date: 2016-03-
|
|
14
|
+
date: 2016-03-18 00:00:00.000000000 Z
|
|
15
15
|
dependencies:
|
|
16
16
|
- !ruby/object:Gem::Dependency
|
|
17
17
|
name: rails
|
|
@@ -752,7 +752,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
|
752
752
|
version: '0'
|
|
753
753
|
requirements: []
|
|
754
754
|
rubyforge_project:
|
|
755
|
-
rubygems_version: 2.
|
|
755
|
+
rubygems_version: 2.4.8
|
|
756
756
|
signing_key:
|
|
757
757
|
specification_version: 4
|
|
758
758
|
summary: A Rails engine for metadata aggregation, enhancement, and quality control.
|
|
@@ -941,3 +941,4 @@ test_files:
|
|
|
941
941
|
- spec/views/krikri/records/index.html.erb_spec.rb
|
|
942
942
|
- spec/views/krikri/records/show.html.erb_spec.rb
|
|
943
943
|
- spec/views/krikri/reports/index.html.erb_spec.rb
|
|
944
|
+
has_rdoc:
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
../../../../solr_conf/schema.xml
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
../../../../solr_conf/solrconfig.xml
|