hydra-core 5.0.0.pre14 → 5.0.0.pre15
Sign up to get free protection for your applications and to get access to all the features.
- data/hydra-core.gemspec +2 -2
- data/lib/generators/hydra/head_generator.rb +1 -1
- data/lib/generators/hydra/templates/fedora_conf/conf/development/fedora.fcfg +391 -459
- data/lib/generators/hydra/templates/fedora_conf/conf/test/fedora.fcfg +391 -459
- data/lib/generators/hydra/templates/solr_conf/conf/schema.xml +482 -73
- data/lib/generators/hydra/templates/solr_conf/conf/solrconfig.xml +196 -42
- data/lib/generators/hydra/templates/solr_conf/solr.xml +1 -1
- data/lib/hydra-head/version.rb +1 -1
- data/spec/controllers/catalog_controller_spec.rb +0 -1
- data/spec/support/lib/generators/test_app_generator.rb +4 -0
- data/spec/support/lib/tasks/rspec.rake +8 -0
- data/tasks/rspec.rake +6 -6
- metadata +9 -7
|
@@ -27,15 +27,35 @@
|
|
|
27
27
|
|
|
28
28
|
For more information, on how to customize this file, please see
|
|
29
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
|
|
30
46
|
-->
|
|
31
47
|
|
|
32
|
-
<schema name="
|
|
48
|
+
<schema name="Hydra" version="1.4">
|
|
33
49
|
<!-- attribute "name" is the name of this schema and is only used for display purposes.
|
|
34
50
|
Applications should change this to reflect the nature of the search collection.
|
|
35
|
-
version="1.
|
|
51
|
+
version="1.4" is Solr's version number for the schema syntax and semantics. It should
|
|
36
52
|
not normally be changed by applications.
|
|
37
53
|
1.0: multiValued attribute did not exist, all fields are multiValued by nature
|
|
38
|
-
1.1: multiValued attribute introduced, false by default
|
|
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
|
+
-->
|
|
39
59
|
|
|
40
60
|
<types>
|
|
41
61
|
<!-- field type definitions. The "name" attribute is
|
|
@@ -46,18 +66,19 @@
|
|
|
46
66
|
org.apache.solr.analysis package.
|
|
47
67
|
-->
|
|
48
68
|
|
|
49
|
-
<!-- The StrField type is not analyzed, but indexed/stored verbatim.
|
|
50
|
-
- StrField and TextField support an optional compressThreshold which
|
|
51
|
-
limits compression (if enabled in the derived fields) to values which
|
|
52
|
-
exceed a certain size (in characters).
|
|
53
|
-
-->
|
|
69
|
+
<!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
|
|
54
70
|
<fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
|
|
55
71
|
|
|
56
72
|
<!-- boolean type: "true" or "false" -->
|
|
57
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"/>
|
|
58
76
|
|
|
59
77
|
<!-- The optional sortMissingLast and sortMissingFirst attributes are
|
|
60
|
-
currently supported on types that are sorted internally as strings
|
|
78
|
+
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.
|
|
61
82
|
- If sortMissingLast="true", then a sort on this field will cause documents
|
|
62
83
|
without the field to come after documents with the field,
|
|
63
84
|
regardless of the requested sort order (asc or desc).
|
|
@@ -69,25 +90,28 @@
|
|
|
69
90
|
field first in an ascending sort and last in a descending sort.
|
|
70
91
|
-->
|
|
71
92
|
|
|
72
|
-
|
|
73
|
-
|
|
74
|
-
|
|
75
|
-
|
|
76
|
-
<fieldType name="
|
|
77
|
-
<fieldType name="long" class="solr.
|
|
78
|
-
<fieldType name="
|
|
79
|
-
|
|
80
|
-
|
|
81
|
-
|
|
82
|
-
|
|
83
|
-
|
|
84
|
-
|
|
85
|
-
|
|
86
|
-
|
|
87
|
-
|
|
88
|
-
|
|
89
|
-
|
|
90
|
-
|
|
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"/>
|
|
91
115
|
|
|
92
116
|
<!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
|
|
93
117
|
is a more restricted form of the canonical representation of dateTime
|
|
@@ -108,18 +132,55 @@
|
|
|
108
132
|
the current day
|
|
109
133
|
|
|
110
134
|
Consult the DateField javadocs for more information.
|
|
135
|
+
|
|
136
|
+
Note: For faster range queries, consider the tdate type
|
|
111
137
|
-->
|
|
112
|
-
<fieldType name="date" class="solr.
|
|
138
|
+
<fieldType name="date" class="solr.TrieDateField" omitNorms="true" precisionStep="0" positionIncrementGap="0"/>
|
|
139
|
+
|
|
140
|
+
<!-- A Trie based date field for faster date range queries and date faceting. -->
|
|
141
|
+
<fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" precisionStep="6" positionIncrementGap="0"/>
|
|
142
|
+
|
|
143
|
+
|
|
144
|
+
<!--
|
|
145
|
+
Note:
|
|
146
|
+
These should only be used for compatibility with existing indexes (created with older Solr versions)
|
|
147
|
+
or if "sortMissingFirst" or "sortMissingLast" functionality is needed. Use Trie based fields instead.
|
|
148
|
+
|
|
149
|
+
Plain numeric field types that store and index the text
|
|
150
|
+
value verbatim (and hence don't support range queries, since the
|
|
151
|
+
lexicographic ordering isn't equal to the numeric ordering)
|
|
152
|
+
-->
|
|
153
|
+
<fieldType name="pint" class="solr.IntField" omitNorms="true"/>
|
|
154
|
+
<fieldType name="plong" class="solr.LongField" omitNorms="true"/>
|
|
155
|
+
<fieldType name="pfloat" class="solr.FloatField" omitNorms="true"/>
|
|
156
|
+
<fieldType name="pdouble" class="solr.DoubleField" omitNorms="true"/>
|
|
157
|
+
<fieldType name="pdate" class="solr.DateField" sortMissingLast="true" omitNorms="true"/>
|
|
158
|
+
|
|
159
|
+
|
|
160
|
+
<!--
|
|
161
|
+
Note:
|
|
162
|
+
These should only be used for compatibility with existing indexes (created with older Solr versions).
|
|
163
|
+
Use Trie based fields instead. As of Solr 3.5 and 4.x, Trie based fields support sortMissingFirst/Last
|
|
164
|
+
|
|
165
|
+
Numeric field types that manipulate the value into
|
|
166
|
+
a string value that isn't human-readable in its internal form,
|
|
167
|
+
but with a lexicographic ordering the same as the numeric ordering,
|
|
168
|
+
so that range queries work correctly.
|
|
169
|
+
-->
|
|
170
|
+
<fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/>
|
|
171
|
+
<fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/>
|
|
172
|
+
<fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/>
|
|
173
|
+
<fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/>
|
|
113
174
|
|
|
114
175
|
|
|
115
176
|
<!-- The "RandomSortField" is not used to store or search any
|
|
116
177
|
data. You can declare fields of this type it in your schema
|
|
117
|
-
to generate
|
|
178
|
+
to generate pseudo-random orderings of your docs for sorting
|
|
118
179
|
purposes. The ordering is generated based on the field name
|
|
119
180
|
and the version of the index, As long as the index version
|
|
120
181
|
remains unchanged, and the same field name is reused,
|
|
121
182
|
the ordering of the docs will be consistent.
|
|
122
|
-
If you want
|
|
183
|
+
If you want different psuedo-random orderings of documents,
|
|
123
184
|
for the same version of the index, use a dynamicField and
|
|
124
185
|
change the name
|
|
125
186
|
-->
|
|
@@ -136,6 +197,14 @@
|
|
|
136
197
|
For more info on customizing your analyzer chain, please see
|
|
137
198
|
http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
|
|
138
199
|
-->
|
|
200
|
+
<fieldType name="text" class="solr.TextField" positionIncrementGap="100">
|
|
201
|
+
<analyzer>
|
|
202
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
203
|
+
<filter class="solr.ICUFoldingFilterFactory" />
|
|
204
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
|
|
205
|
+
<filter class="solr.SnowballPorterFilterFactory" language="English" />
|
|
206
|
+
</analyzer>
|
|
207
|
+
</fieldType>
|
|
139
208
|
|
|
140
209
|
<!-- One can also specify an existing Analyzer class that has a
|
|
141
210
|
default constructor via the class attribute on the analyzer element
|
|
@@ -151,59 +220,176 @@
|
|
|
151
220
|
</analyzer>
|
|
152
221
|
</fieldType>
|
|
153
222
|
|
|
154
|
-
<!-- A text field that
|
|
155
|
-
|
|
156
|
-
|
|
157
|
-
|
|
158
|
-
|
|
159
|
-
|
|
223
|
+
<!-- A general text field that has reasonable, generic
|
|
224
|
+
cross-language defaults: it tokenizes with StandardTokenizer,
|
|
225
|
+
removes stop words from case-insensitive "stopwords.txt"
|
|
226
|
+
(empty by default), and down cases. At query time only, it
|
|
227
|
+
also applies synonyms. -->
|
|
228
|
+
<fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
|
|
229
|
+
<analyzer type="index">
|
|
230
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
231
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
|
|
232
|
+
<!-- in this example, we will only use synonyms at query time
|
|
233
|
+
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
|
|
234
|
+
-->
|
|
235
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
|
236
|
+
</analyzer>
|
|
237
|
+
<analyzer type="query">
|
|
238
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
239
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
|
|
240
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
|
241
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
|
242
|
+
</analyzer>
|
|
243
|
+
</fieldType>
|
|
244
|
+
|
|
245
|
+
<!-- A text field with defaults appropriate for English: it
|
|
246
|
+
tokenizes with StandardTokenizer, removes English stop words
|
|
247
|
+
(stopwords_en.txt), down cases, protects words from protwords.txt, and
|
|
248
|
+
finally applies Porter's stemming. The query time analyzer
|
|
249
|
+
also applies synonyms from synonyms.txt. -->
|
|
250
|
+
<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
|
|
251
|
+
<analyzer type="index">
|
|
252
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
253
|
+
<!-- in this example, we will only use synonyms at query time
|
|
254
|
+
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
|
|
255
|
+
-->
|
|
256
|
+
<!-- Case insensitive stop word removal.
|
|
257
|
+
add enablePositionIncrements=true in both the index and query
|
|
258
|
+
analyzers to leave a 'gap' for more accurate phrase queries.
|
|
160
259
|
-->
|
|
161
|
-
|
|
260
|
+
<filter class="solr.StopFilterFactory"
|
|
261
|
+
ignoreCase="true"
|
|
262
|
+
words="stopwords_en.txt"
|
|
263
|
+
enablePositionIncrements="true"
|
|
264
|
+
/>
|
|
265
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
|
266
|
+
<filter class="solr.EnglishPossessiveFilterFactory"/>
|
|
267
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
|
268
|
+
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
|
|
269
|
+
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
|
270
|
+
-->
|
|
271
|
+
<filter class="solr.PorterStemFilterFactory"/>
|
|
272
|
+
</analyzer>
|
|
273
|
+
<analyzer type="query">
|
|
274
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
275
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
|
276
|
+
<filter class="solr.StopFilterFactory"
|
|
277
|
+
ignoreCase="true"
|
|
278
|
+
words="stopwords_en.txt"
|
|
279
|
+
enablePositionIncrements="true"
|
|
280
|
+
/>
|
|
281
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
|
282
|
+
<filter class="solr.EnglishPossessiveFilterFactory"/>
|
|
283
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
|
284
|
+
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
|
|
285
|
+
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
|
286
|
+
-->
|
|
287
|
+
<filter class="solr.PorterStemFilterFactory"/>
|
|
288
|
+
</analyzer>
|
|
289
|
+
</fieldType>
|
|
290
|
+
|
|
291
|
+
<!-- A text field with defaults appropriate for English, plus
|
|
292
|
+
aggressive word-splitting and autophrase features enabled.
|
|
293
|
+
This field is just like text_en, except it adds
|
|
294
|
+
WordDelimiterFilter to enable splitting and matching of
|
|
295
|
+
words on case-change, alpha numeric boundaries, and
|
|
296
|
+
non-alphanumeric chars. This means certain compound word
|
|
297
|
+
cases will work, for example query "wi fi" will match
|
|
298
|
+
document "WiFi" or "wi-fi". However, other cases will still
|
|
299
|
+
not match, for example if the query is "wifi" and the
|
|
300
|
+
document is "wi fi" or if the query is "wi-fi" and the
|
|
301
|
+
document is "wifi".
|
|
302
|
+
-->
|
|
303
|
+
<fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
|
|
162
304
|
<analyzer type="index">
|
|
163
305
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
164
306
|
<!-- in this example, we will only use synonyms at query time
|
|
165
307
|
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
|
|
166
308
|
-->
|
|
167
309
|
<!-- Case insensitive stop word removal.
|
|
168
|
-
|
|
169
|
-
|
|
310
|
+
add enablePositionIncrements=true in both the index and query
|
|
311
|
+
analyzers to leave a 'gap' for more accurate phrase queries.
|
|
170
312
|
-->
|
|
171
313
|
<filter class="solr.StopFilterFactory"
|
|
172
314
|
ignoreCase="true"
|
|
173
|
-
words="
|
|
315
|
+
words="stopwords_en.txt"
|
|
174
316
|
enablePositionIncrements="true"
|
|
175
317
|
/>
|
|
176
318
|
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
|
|
177
319
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
178
|
-
<filter class="solr.
|
|
179
|
-
<filter class="solr.
|
|
320
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
|
321
|
+
<filter class="solr.PorterStemFilterFactory"/>
|
|
180
322
|
</analyzer>
|
|
181
323
|
<analyzer type="query">
|
|
182
324
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
183
325
|
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
|
184
|
-
<filter class="solr.StopFilterFactory"
|
|
326
|
+
<filter class="solr.StopFilterFactory"
|
|
327
|
+
ignoreCase="true"
|
|
328
|
+
words="stopwords_en.txt"
|
|
329
|
+
enablePositionIncrements="true"
|
|
330
|
+
/>
|
|
185
331
|
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
|
|
186
332
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
187
|
-
<filter class="solr.
|
|
188
|
-
<filter class="solr.
|
|
333
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
|
334
|
+
<filter class="solr.PorterStemFilterFactory"/>
|
|
189
335
|
</analyzer>
|
|
190
336
|
</fieldType>
|
|
191
337
|
|
|
192
|
-
|
|
193
338
|
<!-- Less flexible matching, but less false matches. Probably not ideal for product names,
|
|
194
339
|
but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
|
|
195
|
-
<fieldType name="
|
|
340
|
+
<fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
|
|
196
341
|
<analyzer>
|
|
197
342
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
198
343
|
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
|
|
199
|
-
<filter class="solr.StopFilterFactory" ignoreCase="true" words="
|
|
344
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_en.txt"/>
|
|
200
345
|
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
|
|
201
346
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
202
|
-
<filter class="solr.
|
|
347
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
|
348
|
+
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
|
349
|
+
<!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
|
|
350
|
+
possible with WordDelimiterFilter in conjuncton with stemming. -->
|
|
351
|
+
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
352
|
+
</analyzer>
|
|
353
|
+
</fieldType>
|
|
354
|
+
|
|
355
|
+
<!-- Just like text_general except it reverses the characters of
|
|
356
|
+
each token, to enable more efficient leading wildcard queries. -->
|
|
357
|
+
<fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
|
|
358
|
+
<analyzer type="index">
|
|
359
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
360
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
|
|
361
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
|
362
|
+
<filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
|
|
363
|
+
maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
|
|
364
|
+
</analyzer>
|
|
365
|
+
<analyzer type="query">
|
|
366
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
367
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
|
368
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
|
|
369
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
|
370
|
+
</analyzer>
|
|
371
|
+
</fieldType>
|
|
372
|
+
|
|
373
|
+
<fieldType name="textSpell" class="solr.TextField" positionIncrementGap="100" >
|
|
374
|
+
<analyzer>
|
|
375
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
376
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
|
|
377
|
+
<filter class="solr.StandardFilterFactory"/>
|
|
378
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
|
203
379
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
204
380
|
</analyzer>
|
|
205
381
|
</fieldType>
|
|
206
382
|
|
|
383
|
+
<!-- charFilter + WhitespaceTokenizer -->
|
|
384
|
+
<!--
|
|
385
|
+
<fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
|
|
386
|
+
<analyzer>
|
|
387
|
+
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
|
|
388
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
389
|
+
</analyzer>
|
|
390
|
+
</fieldType>
|
|
391
|
+
-->
|
|
392
|
+
|
|
207
393
|
<!-- This is an example of using the KeywordTokenizer along
|
|
208
394
|
With various TokenFilterFactories to produce a sortable field
|
|
209
395
|
that does not include some properties of the source text
|
|
@@ -223,11 +409,11 @@
|
|
|
223
409
|
<!-- The PatternReplaceFilter gives you the flexibility to use
|
|
224
410
|
Java Regular expression to replace any sequence of characters
|
|
225
411
|
matching a pattern with an arbitrary replacement string,
|
|
226
|
-
which may include back
|
|
412
|
+
which may include back references to portions of the original
|
|
227
413
|
string matched by the pattern.
|
|
228
414
|
|
|
229
415
|
See the Java Regular Expression documentation for more
|
|
230
|
-
|
|
416
|
+
information on pattern and replacement string syntax.
|
|
231
417
|
|
|
232
418
|
http://java.sun.com/j2se/1.5.0/docs/api/java/util/regex/package-summary.html
|
|
233
419
|
-->
|
|
@@ -236,48 +422,271 @@
|
|
|
236
422
|
/>
|
|
237
423
|
</analyzer>
|
|
238
424
|
</fieldType>
|
|
425
|
+
|
|
426
|
+
<fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
|
|
427
|
+
<analyzer>
|
|
428
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
429
|
+
<filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
|
|
430
|
+
</analyzer>
|
|
431
|
+
</fieldtype>
|
|
239
432
|
|
|
240
|
-
|
|
241
|
-
|
|
242
|
-
|
|
243
|
-
|
|
433
|
+
<fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
|
|
434
|
+
<analyzer>
|
|
435
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
436
|
+
<!--
|
|
437
|
+
The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
|
|
438
|
+
a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
|
|
439
|
+
Attributes of the DelimitedPayloadTokenFilterFactory :
|
|
440
|
+
"delimiter" - a one character delimiter. Default is | (pipe)
|
|
441
|
+
"encoder" - how to encode the following value into a playload
|
|
442
|
+
float -> org.apache.lucene.analysis.payloads.FloatEncoder,
|
|
443
|
+
integer -> o.a.l.a.p.IntegerEncoder
|
|
444
|
+
identity -> o.a.l.a.p.IdentityEncoder
|
|
445
|
+
Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
|
|
446
|
+
-->
|
|
447
|
+
<filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
|
|
448
|
+
</analyzer>
|
|
449
|
+
</fieldtype>
|
|
244
450
|
|
|
451
|
+
<!-- lowercases the entire field value, keeping it as a single token. -->
|
|
452
|
+
<fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
|
|
453
|
+
<analyzer>
|
|
454
|
+
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
|
455
|
+
<filter class="solr.LowerCaseFilterFactory" />
|
|
456
|
+
</analyzer>
|
|
457
|
+
</fieldType>
|
|
458
|
+
|
|
459
|
+
<fieldType name="text_path" class="solr.TextField" positionIncrementGap="100">
|
|
460
|
+
<analyzer>
|
|
461
|
+
<tokenizer class="solr.PathHierarchyTokenizerFactory"/>
|
|
462
|
+
</analyzer>
|
|
463
|
+
</fieldType>
|
|
464
|
+
|
|
465
|
+
<!-- since fields of this type are by default not stored or indexed,
|
|
466
|
+
any data added to them will be ignored outright. -->
|
|
467
|
+
<fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
|
|
468
|
+
|
|
469
|
+
<!-- This point type indexes the coordinates as separate fields (subFields)
|
|
470
|
+
If subFieldType is defined, it references a type, and a dynamic field
|
|
471
|
+
definition is created matching *___<typename>. Alternately, if
|
|
472
|
+
subFieldSuffix is defined, that is used to create the subFields.
|
|
473
|
+
Example: if subFieldType="double", then the coordinates would be
|
|
474
|
+
indexed in fields myloc_0___double,myloc_1___double.
|
|
475
|
+
Example: if subFieldSuffix="_d" then the coordinates would be indexed
|
|
476
|
+
in fields myloc_0_d,myloc_1_d
|
|
477
|
+
The subFields are an implementation detail of the fieldType, and end
|
|
478
|
+
users normally should not need to know about them.
|
|
479
|
+
-->
|
|
480
|
+
<fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
|
|
481
|
+
|
|
482
|
+
<!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
|
|
483
|
+
<fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
|
|
484
|
+
|
|
485
|
+
<!--
|
|
486
|
+
A Geohash is a compact representation of a latitude longitude pair in a single field.
|
|
487
|
+
See http://wiki.apache.org/solr/SpatialSearch
|
|
488
|
+
-->
|
|
489
|
+
<fieldtype name="geohash" class="solr.GeoHashField"/>
|
|
245
490
|
</types>
|
|
246
491
|
|
|
247
|
-
<fields>
|
|
248
492
|
|
|
493
|
+
<fields>
|
|
494
|
+
<!-- Valid attributes for fields:
|
|
495
|
+
name: mandatory - the name for the field
|
|
496
|
+
type: mandatory - the name of a previously defined type from the
|
|
497
|
+
<types> section
|
|
498
|
+
indexed: true if this field should be indexed (searchable or sortable)
|
|
499
|
+
stored: true if this field should be retrievable
|
|
500
|
+
multiValued: true if this field may contain multiple values per document
|
|
501
|
+
omitNorms: (expert) set to true to omit the norms associated with
|
|
502
|
+
this field (this disables length normalization and index-time
|
|
503
|
+
boosting for the field, and saves some memory). Only full-text
|
|
504
|
+
fields or fields that need an index-time boost need norms.
|
|
505
|
+
termVectors: [false] set to true to store the term vector for a
|
|
506
|
+
given field.
|
|
507
|
+
When using MoreLikeThis, fields used for similarity should be
|
|
508
|
+
stored for best performance.
|
|
509
|
+
termPositions: Store position information with the term vector.
|
|
510
|
+
This will increase storage costs.
|
|
511
|
+
termOffsets: Store offset information with the term vector. This
|
|
512
|
+
will increase storage costs.
|
|
513
|
+
default: a value that should be used if no value is specified
|
|
514
|
+
when adding a document.
|
|
515
|
+
-->
|
|
516
|
+
|
|
517
|
+
<!-- NOTE: this is not a full list of fields in the index; dynamic fields are also used -->
|
|
249
518
|
<field name="id" type="string" indexed="true" stored="true" required="true" />
|
|
250
|
-
<field name="text" type="text" indexed="true" stored="true" multiValued="true"/>
|
|
251
519
|
<field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
|
|
252
|
-
|
|
253
|
-
|
|
520
|
+
<!-- default, catch all search field -->
|
|
521
|
+
<field name="text" type="text" indexed="true" stored="false" multiValued="true"/>
|
|
522
|
+
|
|
523
|
+
<!-- these display fields are NOT multi-valued -->
|
|
524
|
+
<field name="marc_display" type="string" indexed="false" stored="true" multiValued="false"/>
|
|
525
|
+
<field name="title_display" type="string" indexed="false" stored="true" multiValued="false"/>
|
|
526
|
+
<field name="title_vern_display" type="string" indexed="false" stored="true" multiValued="false"/>
|
|
527
|
+
<field name="subtitle_display" type="string" indexed="false" stored="true" multiValued="false"/>
|
|
528
|
+
<field name="subtitle_vern_display" type="string" indexed="false" stored="true" multiValued="false"/>
|
|
529
|
+
<field name="author_display" type="string" indexed="false" stored="true" multiValued="false"/>
|
|
530
|
+
<field name="author_vern_display" type="string" indexed="false" stored="true" multiValued="false"/>
|
|
531
|
+
|
|
532
|
+
<!-- these fields are also used for display, so they must be stored -->
|
|
533
|
+
<field name="isbn_t" type="text" indexed="true" stored="true" multiValued="true"/>
|
|
534
|
+
<field name="language_facet" type="string" indexed="true" stored="true" multiValued="true" />
|
|
535
|
+
<field name="subject_topic_facet" type="string" indexed="true" stored="true" multiValued="true" />
|
|
536
|
+
<field name="subject_era_facet" type="string" indexed="true" stored="true" multiValued="true" />
|
|
537
|
+
<field name="subject_geo_facet" type="string" indexed="true" stored="true" multiValued="true" />
|
|
538
|
+
<!-- pub_date is used for facet and display so it must be indexed and stored -->
|
|
254
539
|
<field name="pub_date" type="string" indexed="true" stored="true" multiValued="true"/>
|
|
255
|
-
|
|
256
|
-
|
|
540
|
+
<!-- pub_date sort uses new trie-based int fields, which are recommended for any int and are displayable, sortable, and range-quer
|
|
541
|
+
we use 'tint' for faster range-queries. -->
|
|
542
|
+
<field name="pub_date_sort" type="tint" indexed="true" stored="true" multiValued="false"/>
|
|
543
|
+
|
|
257
544
|
<!-- format is used for facet, display, and choosing which partial to use for the show view, so it must be stored and indexed -->
|
|
258
545
|
<field name="format" type="string" indexed="true" stored="true"/>
|
|
546
|
+
|
|
259
547
|
|
|
260
|
-
|
|
548
|
+
|
|
549
|
+
<!-- Dynamic field definitions. If a field name is not found, dynamicFields
|
|
550
|
+
will be used if the name matches any of the patterns.
|
|
551
|
+
RESTRICTION: the glob-like pattern in the name attribute must have
|
|
552
|
+
a "*" only at the start or the end.
|
|
553
|
+
EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
|
|
554
|
+
Longer patterns will be matched first. if equal size patterns
|
|
555
|
+
both match, the first appearing in the schema will be used. -->
|
|
556
|
+
<dynamicField name="*_i" type="int" indexed="true" stored="true"/>
|
|
261
557
|
<dynamicField name="*_s" type="string" indexed="true" stored="true" multiValued="true"/>
|
|
262
|
-
<dynamicField name="*_l" type="
|
|
558
|
+
<dynamicField name="*_l" type="long" indexed="true" stored="true"/>
|
|
263
559
|
<dynamicField name="*_t" type="text" indexed="true" stored="true" multiValued="true"/>
|
|
560
|
+
<dynamicField name="*_txt" type="text_general" indexed="true" stored="true" multiValued="true"/>
|
|
264
561
|
<dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
|
|
265
|
-
<dynamicField name="*_f" type="
|
|
266
|
-
<dynamicField name="*_d" type="
|
|
562
|
+
<dynamicField name="*_f" type="float" indexed="true" stored="true"/>
|
|
563
|
+
<dynamicField name="*_d" type="double" indexed="true" stored="true"/>
|
|
564
|
+
|
|
565
|
+
<!-- Type used to index the lat and lon components for the "location" FieldType -->
|
|
566
|
+
<dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false"/>
|
|
567
|
+
|
|
267
568
|
<dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
|
|
569
|
+
<dynamicField name="*_p" type="location" indexed="true" stored="true"/>
|
|
570
|
+
|
|
571
|
+
<!-- some trie-coded dynamic fields for faster range queries -->
|
|
572
|
+
<dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
|
|
573
|
+
<dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
|
|
574
|
+
<dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
|
|
575
|
+
<dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
|
|
576
|
+
<dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
|
|
577
|
+
|
|
578
|
+
<dynamicField name="*_pi" type="pint" indexed="true" stored="true"/>
|
|
268
579
|
|
|
269
|
-
<dynamicField name="
|
|
580
|
+
<dynamicField name="ignored_*" type="ignored" multiValued="true"/>
|
|
581
|
+
<dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
|
|
270
582
|
|
|
271
|
-
<dynamicField name="*
|
|
272
|
-
<dynamicField name="*_facet" type="string" indexed="true" stored="true" multiValued="true" />
|
|
273
|
-
<dynamicField name="*_display" type="string" indexed="false" stored="true" multiValued="true" />
|
|
583
|
+
<dynamicField name="random_*" type="random" />
|
|
274
584
|
|
|
585
|
+
<dynamicField name="*_display" type="string" indexed="false" stored="true" multiValued="true" />
|
|
586
|
+
<dynamicField name="*_facet" type="string" indexed="true" stored="true" multiValued="true" />
|
|
587
|
+
<dynamicField name="*_sort" type="string" indexed="true" stored="false" multiValued="false" />
|
|
588
|
+
<dynamicField name="*_unstem_search" type="text_general" indexed="true" stored="false" multiValued="true" />
|
|
589
|
+
<dynamicField name="*spell" type="textSpell" indexed="true" stored="false" multiValued="true" />
|
|
590
|
+
|
|
591
|
+
<!-- uncomment the following to ignore any fields that don't already match an existing
|
|
592
|
+
field name or dynamic field, rather than reporting them as an error.
|
|
593
|
+
alternately, change the type="ignored" to some other type e.g. "text" if you want
|
|
594
|
+
unknown fields indexed and/or stored by default -->
|
|
595
|
+
<!--dynamicField name="*" type="ignored" multiValued="true" /-->
|
|
596
|
+
|
|
275
597
|
</fields>
|
|
276
598
|
|
|
599
|
+
<!-- Field to use to determine and enforce document uniqueness.
|
|
600
|
+
Unless this field is marked with required="false", it will be a required field
|
|
601
|
+
-->
|
|
277
602
|
<uniqueKey>id</uniqueKey>
|
|
603
|
+
|
|
604
|
+
<!-- field for the QueryParser to use when an explicit fieldname is absent -->
|
|
278
605
|
<defaultSearchField>text</defaultSearchField>
|
|
279
|
-
|
|
280
|
-
|
|
281
|
-
<
|
|
606
|
+
|
|
607
|
+
<!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
|
|
608
|
+
<solrQueryParser defaultOperator="AND"/>
|
|
609
|
+
|
|
610
|
+
<!-- copyField commands copy one field to another at the time a document
|
|
611
|
+
is added to the index. It's used either to index the same field differently,
|
|
612
|
+
or to add multiple fields to the same field for easier/faster searching. -->
|
|
613
|
+
<!-- Copy Fields -->
|
|
614
|
+
|
|
615
|
+
<!-- unstemmed fields -->
|
|
616
|
+
<copyField source="title_t" dest="title_unstem_search"/>
|
|
617
|
+
<copyField source="subtitle_t" dest="subtitle_unstem_search"/>
|
|
618
|
+
<copyField source="title_addl_t" dest="title_addl_unstem_search"/>
|
|
619
|
+
<copyField source="title_added_entry_t" dest="title_added_entry_unstem_search"/>
|
|
620
|
+
<copyField source="title_series_t" dest="title_series_unstem_search"/>
|
|
621
|
+
<copyField source="author_t" dest="author_unstem_search"/>
|
|
622
|
+
<copyField source="author_addl_t" dest="author_addl_unstem_search"/>
|
|
623
|
+
<copyField source="subject_t" dest="subject_unstem_search"/>
|
|
624
|
+
<copyField source="subject_addl_t" dest="subject_addl_unstem_search"/>
|
|
625
|
+
<copyField source="subject_topic_facet" dest="subject_topic_unstem_search"/>
|
|
626
|
+
|
|
627
|
+
<!-- sort fields -->
|
|
628
|
+
<copyField source="pub_date" dest="pub_date_sort"/>
|
|
629
|
+
|
|
630
|
+
|
|
631
|
+
<!-- spellcheck fields -->
|
|
632
|
+
<!-- default spell check; should match fields for default request handler -->
|
|
633
|
+
<!-- it won't work with a copy of a copy field -->
|
|
634
|
+
<copyField source="*_t" dest="spell"/>
|
|
635
|
+
<copyField source="*_facet" dest="spell"/>
|
|
636
|
+
<!-- title spell check; should match fields for title request handler -->
|
|
637
|
+
<copyField source="title_t" dest="title_spell"/>
|
|
638
|
+
<copyField source="subtitle_t" dest="title_spell"/>
|
|
639
|
+
<copyField source="addl_titles_t" dest="title_spell"/>
|
|
640
|
+
<copyField source="title_added_entry_t" dest="title_spell"/>
|
|
641
|
+
<copyField source="title_series_t" dest="title_spell"/>
|
|
642
|
+
<!-- author spell check; should match fields for author request handler -->
|
|
643
|
+
<copyField source="author_t" dest="author_spell"/>
|
|
644
|
+
<copyField source="author_addl_t" dest="author_spell"/>
|
|
645
|
+
<!-- subject spell check; should match fields for subject request handler -->
|
|
646
|
+
<copyField source="subject_topic_facet" dest="subject_spell"/>
|
|
647
|
+
<copyField source="subject_t" dest="subject_spell"/>
|
|
648
|
+
<copyField source="subject_addl_t" dest="subject_spell"/>
|
|
649
|
+
|
|
650
|
+
<!-- OpenSearch query field should match request handler search fields -->
|
|
651
|
+
<copyField source="title_t" dest="opensearch_display"/>
|
|
652
|
+
<copyField source="subtitle_t" dest="opensearch_display"/>
|
|
653
|
+
<copyField source="addl_titles_t" dest="opensearch_display"/>
|
|
654
|
+
<copyField source="title_added_entry_t" dest="opensearch_display"/>
|
|
655
|
+
<copyField source="title_series_t" dest="opensearch_display"/>
|
|
656
|
+
<copyField source="author_t" dest="opensearch_display"/>
|
|
657
|
+
<copyField source="author_addl_t" dest="opensearch_display"/>
|
|
658
|
+
<copyField source="subject_topic_facet" dest="opensearch_display"/>
|
|
659
|
+
<copyField source="subject_t" dest="opensearch_display"/>
|
|
660
|
+
<copyField source="subject_addl_t" dest="opensearch_display"/>
|
|
661
|
+
|
|
662
|
+
|
|
663
|
+
<!-- Above, multiple source fields are copied to the [text] field.
|
|
664
|
+
Another way to map multiple source fields to the same
|
|
665
|
+
destination field is to use the dynamic field syntax.
|
|
666
|
+
copyField also supports a maxChars to copy setting. -->
|
|
667
|
+
|
|
668
|
+
<!-- <copyField source="*_t" dest="text" maxChars="3000"/> -->
|
|
669
|
+
<copyField source="*_s" dest="text"/>
|
|
670
|
+
<copyField source="*_t" dest="text"/>
|
|
671
|
+
<copyField source="*_facet" dest="text"/>
|
|
672
|
+
|
|
673
|
+
<!-- copy name to alphaNameSort, a field designed for sorting by name -->
|
|
674
|
+
<!-- <copyField source="name" dest="alphaNameSort"/> -->
|
|
675
|
+
|
|
676
|
+
|
|
677
|
+
<!-- Similarity is the scoring routine for each document vs. a query.
|
|
678
|
+
A custom similarity may be specified here, but the default is fine
|
|
679
|
+
for most applications. -->
|
|
680
|
+
<!-- <similarity class="org.apache.lucene.search.DefaultSimilarity"/> -->
|
|
681
|
+
<!-- ... OR ...
|
|
682
|
+
Specify a SimilarityFactory class name implementation
|
|
683
|
+
allowing parameters to be used.
|
|
684
|
+
-->
|
|
685
|
+
<!--
|
|
686
|
+
<similarity class="com.example.solr.CustomSimilarityFactory">
|
|
687
|
+
<str name="paramkey">param value</str>
|
|
688
|
+
</similarity>
|
|
689
|
+
-->
|
|
690
|
+
|
|
282
691
|
|
|
283
692
|
</schema>
|