supernova 0.2.1 → 0.2.2
Sign up to get free protection for your applications and to get access to all the features.
- data/Gemfile +1 -0
- data/Gemfile.lock +2 -0
- data/VERSION +1 -1
- data/lib/supernova/criteria.rb +6 -2
- data/lib/supernova/solr.rb +1 -0
- data/lib/supernova/solr_criteria.rb +10 -1
- data/lib/supernova/solr_indexer.rb +71 -0
- data/solr/conf/admin-extra.html +31 -0
- data/solr/conf/elevate.xml +36 -0
- data/solr/conf/mapping-FoldToASCII.txt +3813 -0
- data/solr/conf/mapping-ISOLatin1Accent.txt +246 -0
- data/solr/conf/protwords.txt +21 -0
- data/solr/conf/schema.xml +475 -0
- data/solr/conf/scripts.conf +24 -0
- data/solr/conf/solrconfig.xml +1508 -0
- data/solr/conf/spellings.txt +2 -0
- data/solr/conf/stopwords.txt +58 -0
- data/solr/conf/synonyms.txt +29 -0
- data/solr/conf/velocity/VM_global_library.vm +184 -0
- data/solr/conf/velocity/browse.vm +45 -0
- data/solr/conf/velocity/cluster.vm +26 -0
- data/solr/conf/velocity/clusterResults.vm +29 -0
- data/solr/conf/velocity/doc.vm +29 -0
- data/solr/conf/velocity/facet_dates.vm +0 -0
- data/solr/conf/velocity/facet_fields.vm +12 -0
- data/solr/conf/velocity/facet_queries.vm +3 -0
- data/solr/conf/velocity/facet_ranges.vm +30 -0
- data/solr/conf/velocity/facets.vm +7 -0
- data/solr/conf/velocity/footer.vm +17 -0
- data/solr/conf/velocity/head.vm +45 -0
- data/solr/conf/velocity/header.vm +3 -0
- data/solr/conf/velocity/hit.vm +5 -0
- data/solr/conf/velocity/jquery.autocomplete.css +48 -0
- data/solr/conf/velocity/jquery.autocomplete.js +762 -0
- data/solr/conf/velocity/layout.vm +20 -0
- data/solr/conf/velocity/main.css +184 -0
- data/solr/conf/velocity/query.vm +56 -0
- data/solr/conf/velocity/querySpatial.vm +40 -0
- data/solr/conf/velocity/suggest.vm +3 -0
- data/solr/conf/velocity/tabs.vm +22 -0
- data/solr/conf/xslt/example.xsl +132 -0
- data/solr/conf/xslt/example_atom.xsl +67 -0
- data/solr/conf/xslt/example_rss.xsl +66 -0
- data/solr/conf/xslt/luke.xsl +337 -0
- data/spec/integration/solr_spec.rb +6 -0
- data/spec/spec_helper.rb +1 -1
- data/spec/supernova/solr_criteria_spec.rb +16 -0
- data/spec/supernova/solr_indexer_spec.rb +167 -0
- data/supernova.gemspec +45 -3
- metadata +91 -36
@@ -0,0 +1,246 @@
|
|
1
|
+
# The ASF licenses this file to You under the Apache License, Version 2.0
|
2
|
+
# (the "License"); you may not use this file except in compliance with
|
3
|
+
# the License. You may obtain a copy of the License at
|
4
|
+
#
|
5
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
6
|
+
#
|
7
|
+
# Unless required by applicable law or agreed to in writing, software
|
8
|
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
9
|
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
10
|
+
# See the License for the specific language governing permissions and
|
11
|
+
# limitations under the License.
|
12
|
+
|
13
|
+
# Syntax:
|
14
|
+
# "source" => "target"
|
15
|
+
# "source".length() > 0 (source cannot be empty.)
|
16
|
+
# "target".length() >= 0 (target can be empty.)
|
17
|
+
|
18
|
+
# example:
|
19
|
+
# "À" => "A"
|
20
|
+
# "\u00C0" => "A"
|
21
|
+
# "\u00C0" => "\u0041"
|
22
|
+
# "ß" => "ss"
|
23
|
+
# "\t" => " "
|
24
|
+
# "\n" => ""
|
25
|
+
|
26
|
+
# À => A
|
27
|
+
"\u00C0" => "A"
|
28
|
+
|
29
|
+
# Á => A
|
30
|
+
"\u00C1" => "A"
|
31
|
+
|
32
|
+
# Â => A
|
33
|
+
"\u00C2" => "A"
|
34
|
+
|
35
|
+
# Ã => A
|
36
|
+
"\u00C3" => "A"
|
37
|
+
|
38
|
+
# Ä => A
|
39
|
+
"\u00C4" => "A"
|
40
|
+
|
41
|
+
# Å => A
|
42
|
+
"\u00C5" => "A"
|
43
|
+
|
44
|
+
# Æ => AE
|
45
|
+
"\u00C6" => "AE"
|
46
|
+
|
47
|
+
# Ç => C
|
48
|
+
"\u00C7" => "C"
|
49
|
+
|
50
|
+
# È => E
|
51
|
+
"\u00C8" => "E"
|
52
|
+
|
53
|
+
# É => E
|
54
|
+
"\u00C9" => "E"
|
55
|
+
|
56
|
+
# Ê => E
|
57
|
+
"\u00CA" => "E"
|
58
|
+
|
59
|
+
# Ë => E
|
60
|
+
"\u00CB" => "E"
|
61
|
+
|
62
|
+
# Ì => I
|
63
|
+
"\u00CC" => "I"
|
64
|
+
|
65
|
+
# Í => I
|
66
|
+
"\u00CD" => "I"
|
67
|
+
|
68
|
+
# Î => I
|
69
|
+
"\u00CE" => "I"
|
70
|
+
|
71
|
+
# Ï => I
|
72
|
+
"\u00CF" => "I"
|
73
|
+
|
74
|
+
# IJ => IJ
|
75
|
+
"\u0132" => "IJ"
|
76
|
+
|
77
|
+
# Ð => D
|
78
|
+
"\u00D0" => "D"
|
79
|
+
|
80
|
+
# Ñ => N
|
81
|
+
"\u00D1" => "N"
|
82
|
+
|
83
|
+
# Ò => O
|
84
|
+
"\u00D2" => "O"
|
85
|
+
|
86
|
+
# Ó => O
|
87
|
+
"\u00D3" => "O"
|
88
|
+
|
89
|
+
# Ô => O
|
90
|
+
"\u00D4" => "O"
|
91
|
+
|
92
|
+
# Õ => O
|
93
|
+
"\u00D5" => "O"
|
94
|
+
|
95
|
+
# Ö => O
|
96
|
+
"\u00D6" => "O"
|
97
|
+
|
98
|
+
# Ø => O
|
99
|
+
"\u00D8" => "O"
|
100
|
+
|
101
|
+
# Œ => OE
|
102
|
+
"\u0152" => "OE"
|
103
|
+
|
104
|
+
# Þ
|
105
|
+
"\u00DE" => "TH"
|
106
|
+
|
107
|
+
# Ù => U
|
108
|
+
"\u00D9" => "U"
|
109
|
+
|
110
|
+
# Ú => U
|
111
|
+
"\u00DA" => "U"
|
112
|
+
|
113
|
+
# Û => U
|
114
|
+
"\u00DB" => "U"
|
115
|
+
|
116
|
+
# Ü => U
|
117
|
+
"\u00DC" => "U"
|
118
|
+
|
119
|
+
# Ý => Y
|
120
|
+
"\u00DD" => "Y"
|
121
|
+
|
122
|
+
# Ÿ => Y
|
123
|
+
"\u0178" => "Y"
|
124
|
+
|
125
|
+
# à => a
|
126
|
+
"\u00E0" => "a"
|
127
|
+
|
128
|
+
# á => a
|
129
|
+
"\u00E1" => "a"
|
130
|
+
|
131
|
+
# â => a
|
132
|
+
"\u00E2" => "a"
|
133
|
+
|
134
|
+
# ã => a
|
135
|
+
"\u00E3" => "a"
|
136
|
+
|
137
|
+
# ä => a
|
138
|
+
"\u00E4" => "a"
|
139
|
+
|
140
|
+
# å => a
|
141
|
+
"\u00E5" => "a"
|
142
|
+
|
143
|
+
# æ => ae
|
144
|
+
"\u00E6" => "ae"
|
145
|
+
|
146
|
+
# ç => c
|
147
|
+
"\u00E7" => "c"
|
148
|
+
|
149
|
+
# è => e
|
150
|
+
"\u00E8" => "e"
|
151
|
+
|
152
|
+
# é => e
|
153
|
+
"\u00E9" => "e"
|
154
|
+
|
155
|
+
# ê => e
|
156
|
+
"\u00EA" => "e"
|
157
|
+
|
158
|
+
# ë => e
|
159
|
+
"\u00EB" => "e"
|
160
|
+
|
161
|
+
# ì => i
|
162
|
+
"\u00EC" => "i"
|
163
|
+
|
164
|
+
# í => i
|
165
|
+
"\u00ED" => "i"
|
166
|
+
|
167
|
+
# î => i
|
168
|
+
"\u00EE" => "i"
|
169
|
+
|
170
|
+
# ï => i
|
171
|
+
"\u00EF" => "i"
|
172
|
+
|
173
|
+
# ij => ij
|
174
|
+
"\u0133" => "ij"
|
175
|
+
|
176
|
+
# ð => d
|
177
|
+
"\u00F0" => "d"
|
178
|
+
|
179
|
+
# ñ => n
|
180
|
+
"\u00F1" => "n"
|
181
|
+
|
182
|
+
# ò => o
|
183
|
+
"\u00F2" => "o"
|
184
|
+
|
185
|
+
# ó => o
|
186
|
+
"\u00F3" => "o"
|
187
|
+
|
188
|
+
# ô => o
|
189
|
+
"\u00F4" => "o"
|
190
|
+
|
191
|
+
# õ => o
|
192
|
+
"\u00F5" => "o"
|
193
|
+
|
194
|
+
# ö => o
|
195
|
+
"\u00F6" => "o"
|
196
|
+
|
197
|
+
# ø => o
|
198
|
+
"\u00F8" => "o"
|
199
|
+
|
200
|
+
# œ => oe
|
201
|
+
"\u0153" => "oe"
|
202
|
+
|
203
|
+
# ß => ss
|
204
|
+
"\u00DF" => "ss"
|
205
|
+
|
206
|
+
# þ => th
|
207
|
+
"\u00FE" => "th"
|
208
|
+
|
209
|
+
# ù => u
|
210
|
+
"\u00F9" => "u"
|
211
|
+
|
212
|
+
# ú => u
|
213
|
+
"\u00FA" => "u"
|
214
|
+
|
215
|
+
# û => u
|
216
|
+
"\u00FB" => "u"
|
217
|
+
|
218
|
+
# ü => u
|
219
|
+
"\u00FC" => "u"
|
220
|
+
|
221
|
+
# ý => y
|
222
|
+
"\u00FD" => "y"
|
223
|
+
|
224
|
+
# ÿ => y
|
225
|
+
"\u00FF" => "y"
|
226
|
+
|
227
|
+
# ff => ff
|
228
|
+
"\uFB00" => "ff"
|
229
|
+
|
230
|
+
# fi => fi
|
231
|
+
"\uFB01" => "fi"
|
232
|
+
|
233
|
+
# fl => fl
|
234
|
+
"\uFB02" => "fl"
|
235
|
+
|
236
|
+
# ffi => ffi
|
237
|
+
"\uFB03" => "ffi"
|
238
|
+
|
239
|
+
# ffl => ffl
|
240
|
+
"\uFB04" => "ffl"
|
241
|
+
|
242
|
+
# ſt => ft
|
243
|
+
"\uFB05" => "ft"
|
244
|
+
|
245
|
+
# st => st
|
246
|
+
"\uFB06" => "st"
|
@@ -0,0 +1,21 @@
|
|
1
|
+
# The ASF licenses this file to You under the Apache License, Version 2.0
|
2
|
+
# (the "License"); you may not use this file except in compliance with
|
3
|
+
# the License. You may obtain a copy of the License at
|
4
|
+
#
|
5
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
6
|
+
#
|
7
|
+
# Unless required by applicable law or agreed to in writing, software
|
8
|
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
9
|
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
10
|
+
# See the License for the specific language governing permissions and
|
11
|
+
# limitations under the License.
|
12
|
+
|
13
|
+
#-----------------------------------------------------------------------
|
14
|
+
# Use a protected word file to protect against the stemmer reducing two
|
15
|
+
# unrelated words to the same base word.
|
16
|
+
|
17
|
+
# Some non-words that normally won't be encountered,
|
18
|
+
# just to test that they won't be stemmed.
|
19
|
+
dontstems
|
20
|
+
zwhacky
|
21
|
+
|
@@ -0,0 +1,475 @@
|
|
1
|
+
<?xml version="1.0" encoding="UTF-8" ?>
|
2
|
+
<!--
|
3
|
+
Licensed to the Apache Software Foundation (ASF) under one or more
|
4
|
+
contributor license agreements. See the NOTICE file distributed with
|
5
|
+
this work for additional information regarding copyright ownership.
|
6
|
+
The ASF licenses this file to You under the Apache License, Version 2.0
|
7
|
+
(the "License"); you may not use this file except in compliance with
|
8
|
+
the License. You may obtain a copy of the License at
|
9
|
+
|
10
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
11
|
+
|
12
|
+
Unless required by applicable law or agreed to in writing, software
|
13
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
14
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
15
|
+
See the License for the specific language governing permissions and
|
16
|
+
limitations under the License.
|
17
|
+
-->
|
18
|
+
|
19
|
+
<!--
|
20
|
+
This is the Solr schema file. This file should be named "schema.xml" and
|
21
|
+
should be in the conf directory under the solr home
|
22
|
+
(i.e. ./solr/conf/schema.xml by default)
|
23
|
+
or located where the classloader for the Solr webapp can find it.
|
24
|
+
|
25
|
+
This example schema is the recommended starting point for users.
|
26
|
+
It should be kept correct and concise, usable out-of-the-box.
|
27
|
+
|
28
|
+
For more information, on how to customize this file, please see
|
29
|
+
http://wiki.apache.org/solr/SchemaXml
|
30
|
+
|
31
|
+
PERFORMANCE NOTE: this schema includes many optional features and should not
|
32
|
+
be used for benchmarking. To improve performance one could
|
33
|
+
- set stored="false" for all fields possible (esp large fields) when you
|
34
|
+
only need to search on the field but don't need to return the original
|
35
|
+
value.
|
36
|
+
- set indexed="false" if you don't need to search on the field, but only
|
37
|
+
return the field as a result of searching on other indexed fields.
|
38
|
+
- remove all unneeded copyField statements
|
39
|
+
- for best index size and searching performance, set "index" to false
|
40
|
+
for all general text fields, use copyField to copy them to the
|
41
|
+
catchall "text" field, and use that for searching.
|
42
|
+
- For maximum indexing performance, use the StreamingUpdateSolrServer
|
43
|
+
java client.
|
44
|
+
- Remember to run the JVM in server mode, and use a higher logging level
|
45
|
+
that avoids logging every request
|
46
|
+
-->
|
47
|
+
|
48
|
+
<schema name="example" version="1.3">
|
49
|
+
<!-- attribute "name" is the name of this schema and is only used for display purposes.
|
50
|
+
Applications should change this to reflect the nature of the search collection.
|
51
|
+
version="1.2" is Solr's version number for the schema syntax and semantics. It should
|
52
|
+
not normally be changed by applications.
|
53
|
+
1.0: multiValued attribute did not exist, all fields are multiValued by nature
|
54
|
+
1.1: multiValued attribute introduced, false by default
|
55
|
+
1.2: omitTermFreqAndPositions attribute introduced, true by default except for text fields.
|
56
|
+
1.3: removed optional field compress feature
|
57
|
+
-->
|
58
|
+
|
59
|
+
<types>
|
60
|
+
<!-- field type definitions. The "name" attribute is
|
61
|
+
just a label to be used by field definitions. The "class"
|
62
|
+
attribute and any other attributes determine the real
|
63
|
+
behavior of the fieldType.
|
64
|
+
Class names starting with "solr" refer to java classes in the
|
65
|
+
org.apache.solr.analysis package.
|
66
|
+
-->
|
67
|
+
|
68
|
+
<!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
|
69
|
+
<fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
|
70
|
+
|
71
|
+
<!-- boolean type: "true" or "false" -->
|
72
|
+
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
|
73
|
+
<!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
|
74
|
+
<fieldtype name="binary" class="solr.BinaryField"/>
|
75
|
+
|
76
|
+
<!-- The optional sortMissingLast and sortMissingFirst attributes are
|
77
|
+
currently supported on types that are sorted internally as strings.
|
78
|
+
This includes "string","boolean","sint","slong","sfloat","sdouble","pdate"
|
79
|
+
- If sortMissingLast="true", then a sort on this field will cause documents
|
80
|
+
without the field to come after documents with the field,
|
81
|
+
regardless of the requested sort order (asc or desc).
|
82
|
+
- If sortMissingFirst="true", then a sort on this field will cause documents
|
83
|
+
without the field to come before documents with the field,
|
84
|
+
regardless of the requested sort order.
|
85
|
+
- If sortMissingLast="false" and sortMissingFirst="false" (the default),
|
86
|
+
then default lucene sorting will be used which places docs without the
|
87
|
+
field first in an ascending sort and last in a descending sort.
|
88
|
+
-->
|
89
|
+
|
90
|
+
<!--
|
91
|
+
Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
|
92
|
+
-->
|
93
|
+
<fieldType name="int" class="solr.TrieIntField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
|
94
|
+
<fieldType name="float" class="solr.TrieFloatField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
|
95
|
+
<fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
|
96
|
+
<fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
|
97
|
+
|
98
|
+
<!--
|
99
|
+
Numeric field types that index each value at various levels of precision
|
100
|
+
to accelerate range queries when the number of values between the range
|
101
|
+
endpoints is large. See the javadoc for NumericRangeQuery for internal
|
102
|
+
implementation details.
|
103
|
+
|
104
|
+
Smaller precisionStep values (specified in bits) will lead to more tokens
|
105
|
+
indexed per value, slightly larger index size, and faster range queries.
|
106
|
+
A precisionStep of 0 disables indexing at different precision levels.
|
107
|
+
-->
|
108
|
+
<fieldType name="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
|
109
|
+
<fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
|
110
|
+
<fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
|
111
|
+
<fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
|
112
|
+
|
113
|
+
<!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
|
114
|
+
is a more restricted form of the canonical representation of dateTime
|
115
|
+
http://www.w3.org/TR/xmlschema-2/#dateTime
|
116
|
+
The trailing "Z" designates UTC time and is mandatory.
|
117
|
+
Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
|
118
|
+
All other components are mandatory.
|
119
|
+
|
120
|
+
Expressions can also be used to denote calculations that should be
|
121
|
+
performed relative to "NOW" to determine the value, ie...
|
122
|
+
|
123
|
+
NOW/HOUR
|
124
|
+
... Round to the start of the current hour
|
125
|
+
NOW-1DAY
|
126
|
+
... Exactly 1 day prior to now
|
127
|
+
NOW/DAY+6MONTHS+3DAYS
|
128
|
+
... 6 months and 3 days in the future from the start of
|
129
|
+
the current day
|
130
|
+
|
131
|
+
Consult the DateField javadocs for more information.
|
132
|
+
|
133
|
+
Note: For faster range queries, consider the tdate type
|
134
|
+
-->
|
135
|
+
<fieldType name="date" class="solr.TrieDateField" omitNorms="true" precisionStep="0" positionIncrementGap="0"/>
|
136
|
+
|
137
|
+
<!-- A Trie based date field for faster date range queries and date faceting. -->
|
138
|
+
<fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" precisionStep="6" positionIncrementGap="0"/>
|
139
|
+
|
140
|
+
|
141
|
+
<!--
|
142
|
+
Note:
|
143
|
+
These should only be used for compatibility with existing indexes (created with older Solr versions)
|
144
|
+
or if "sortMissingFirst" or "sortMissingLast" functionality is needed. Use Trie based fields instead.
|
145
|
+
|
146
|
+
Plain numeric field types that store and index the text
|
147
|
+
value verbatim (and hence don't support range queries, since the
|
148
|
+
lexicographic ordering isn't equal to the numeric ordering)
|
149
|
+
-->
|
150
|
+
<fieldType name="pint" class="solr.IntField" omitNorms="true"/>
|
151
|
+
<fieldType name="plong" class="solr.LongField" omitNorms="true"/>
|
152
|
+
<fieldType name="pfloat" class="solr.FloatField" omitNorms="true"/>
|
153
|
+
<fieldType name="pdouble" class="solr.DoubleField" omitNorms="true"/>
|
154
|
+
<fieldType name="pdate" class="solr.DateField" sortMissingLast="true" omitNorms="true"/>
|
155
|
+
<fieldType name="nGram" class="solr.TextField" positionIncrementGap="100" stored="false" multiValued="true">
|
156
|
+
<analyzer type="index">
|
157
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
158
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
159
|
+
<filter class="solr.NGramFilterFactory" minGramSize="2" maxGramSize="15"/>
|
160
|
+
</analyzer>
|
161
|
+
<analyzer type="query">
|
162
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
163
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
164
|
+
</analyzer>
|
165
|
+
</fieldType>
|
166
|
+
|
167
|
+
<!--
|
168
|
+
Note:
|
169
|
+
These should only be used for compatibility with existing indexes (created with older Solr versions)
|
170
|
+
or if "sortMissingFirst" or "sortMissingLast" functionality is needed. Use Trie based fields instead.
|
171
|
+
|
172
|
+
Numeric field types that manipulate the value into
|
173
|
+
a string value that isn't human-readable in its internal form,
|
174
|
+
but with a lexicographic ordering the same as the numeric ordering,
|
175
|
+
so that range queries work correctly.
|
176
|
+
-->
|
177
|
+
<fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/>
|
178
|
+
<fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/>
|
179
|
+
<fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/>
|
180
|
+
<fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/>
|
181
|
+
|
182
|
+
|
183
|
+
<!-- The "RandomSortField" is not used to store or search any
|
184
|
+
data. You can declare fields of this type it in your schema
|
185
|
+
to generate pseudo-random orderings of your docs for sorting
|
186
|
+
purposes. The ordering is generated based on the field name
|
187
|
+
and the version of the index, As long as the index version
|
188
|
+
remains unchanged, and the same field name is reused,
|
189
|
+
the ordering of the docs will be consistent.
|
190
|
+
If you want different psuedo-random orderings of documents,
|
191
|
+
for the same version of the index, use a dynamicField and
|
192
|
+
change the name
|
193
|
+
-->
|
194
|
+
<fieldType name="random" class="solr.RandomSortField" indexed="true" />
|
195
|
+
|
196
|
+
<!-- solr.TextField allows the specification of custom text analyzers
|
197
|
+
specified as a tokenizer and a list of token filters. Different
|
198
|
+
analyzers may be specified for indexing and querying.
|
199
|
+
|
200
|
+
The optional positionIncrementGap puts space between multiple fields of
|
201
|
+
this type on the same document, with the purpose of preventing false phrase
|
202
|
+
matching across fields.
|
203
|
+
|
204
|
+
For more info on customizing your analyzer chain, please see
|
205
|
+
http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
|
206
|
+
-->
|
207
|
+
|
208
|
+
<!-- One can also specify an existing Analyzer class that has a
|
209
|
+
default constructor via the class attribute on the analyzer element
|
210
|
+
<fieldType name="text_greek" class="solr.TextField">
|
211
|
+
<analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
|
212
|
+
</fieldType>
|
213
|
+
-->
|
214
|
+
|
215
|
+
<!-- A text field that only splits on whitespace for exact matching of words -->
|
216
|
+
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
|
217
|
+
<analyzer>
|
218
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
219
|
+
</analyzer>
|
220
|
+
</fieldType>
|
221
|
+
|
222
|
+
<!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
|
223
|
+
words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
|
224
|
+
so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
|
225
|
+
Synonyms and stopwords are customized by external files, and stemming is enabled.
|
226
|
+
The attribute autoGeneratePhraseQueries="true" (the default) causes words that get split to
|
227
|
+
form phrase queries. For example, WordDelimiterFilter splitting text:pdp-11 will cause the parser
|
228
|
+
to generate text:"pdp 11" rather than (text:PDP OR text:11).
|
229
|
+
NOTE: autoGeneratePhraseQueries="true" tends to not work well for non whitespace delimited languages.
|
230
|
+
-->
|
231
|
+
<fieldType name="text" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
|
232
|
+
<analyzer type="index">
|
233
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
234
|
+
<!-- in this example, we will only use synonyms at query time
|
235
|
+
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
|
236
|
+
-->
|
237
|
+
<!-- Case insensitive stop word removal.
|
238
|
+
add enablePositionIncrements=true in both the index and query
|
239
|
+
analyzers to leave a 'gap' for more accurate phrase queries.
|
240
|
+
-->
|
241
|
+
<filter class="solr.StopFilterFactory"
|
242
|
+
ignoreCase="true"
|
243
|
+
words="stopwords.txt"
|
244
|
+
enablePositionIncrements="true"
|
245
|
+
/>
|
246
|
+
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
|
247
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
248
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
249
|
+
<filter class="solr.PorterStemFilterFactory"/>
|
250
|
+
</analyzer>
|
251
|
+
<analyzer type="query">
|
252
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
253
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
254
|
+
<filter class="solr.StopFilterFactory"
|
255
|
+
ignoreCase="true"
|
256
|
+
words="stopwords.txt"
|
257
|
+
enablePositionIncrements="true"
|
258
|
+
/>
|
259
|
+
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
|
260
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
261
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
262
|
+
<filter class="solr.PorterStemFilterFactory"/>
|
263
|
+
</analyzer>
|
264
|
+
</fieldType>
|
265
|
+
|
266
|
+
|
267
|
+
<!-- Less flexible matching, but less false matches. Probably not ideal for product names,
|
268
|
+
but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
|
269
|
+
<fieldType name="textTight" class="solr.TextField" positionIncrementGap="100" >
|
270
|
+
<analyzer>
|
271
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
272
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
|
273
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
|
274
|
+
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
|
275
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
276
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
277
|
+
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
278
|
+
<!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
|
279
|
+
possible with WordDelimiterFilter in conjuncton with stemming. -->
|
280
|
+
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
281
|
+
</analyzer>
|
282
|
+
</fieldType>
|
283
|
+
|
284
|
+
|
285
|
+
<!-- A general unstemmed text field - good if one does not know the language of the field -->
|
286
|
+
<fieldType name="textgen" class="solr.TextField" positionIncrementGap="100">
|
287
|
+
<analyzer type="index">
|
288
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
289
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
|
290
|
+
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
|
291
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
292
|
+
</analyzer>
|
293
|
+
<analyzer type="query">
|
294
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
295
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
296
|
+
<filter class="solr.StopFilterFactory"
|
297
|
+
ignoreCase="true"
|
298
|
+
words="stopwords.txt"
|
299
|
+
enablePositionIncrements="true"
|
300
|
+
/>
|
301
|
+
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
|
302
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
303
|
+
</analyzer>
|
304
|
+
</fieldType>
|
305
|
+
|
306
|
+
|
307
|
+
<!-- A general unstemmed text field that indexes tokens normally and also
|
308
|
+
reversed (via ReversedWildcardFilterFactory), to enable more efficient
|
309
|
+
leading wildcard queries. -->
|
310
|
+
<fieldType name="text_rev" class="solr.TextField" positionIncrementGap="100">
|
311
|
+
<analyzer type="index">
|
312
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
313
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
|
314
|
+
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
|
315
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
316
|
+
<filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
|
317
|
+
maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
|
318
|
+
</analyzer>
|
319
|
+
<analyzer type="query">
|
320
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
321
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
322
|
+
<filter class="solr.StopFilterFactory"
|
323
|
+
ignoreCase="true"
|
324
|
+
words="stopwords.txt"
|
325
|
+
enablePositionIncrements="true"
|
326
|
+
/>
|
327
|
+
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
|
328
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
329
|
+
</analyzer>
|
330
|
+
</fieldType>
|
331
|
+
|
332
|
+
<!-- charFilter + WhitespaceTokenizer -->
|
333
|
+
<!--
|
334
|
+
<fieldType name="textCharNorm" class="solr.TextField" positionIncrementGap="100" >
|
335
|
+
<analyzer>
|
336
|
+
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
|
337
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
338
|
+
</analyzer>
|
339
|
+
</fieldType>
|
340
|
+
-->
|
341
|
+
|
342
|
+
<!-- This is an example of using the KeywordTokenizer along
|
343
|
+
With various TokenFilterFactories to produce a sortable field
|
344
|
+
that does not include some properties of the source text
|
345
|
+
-->
|
346
|
+
<fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
|
347
|
+
<analyzer>
|
348
|
+
<!-- KeywordTokenizer does no actual tokenizing, so the entire
|
349
|
+
input string is preserved as a single token
|
350
|
+
-->
|
351
|
+
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
352
|
+
<!-- The LowerCase TokenFilter does what you expect, which can be
|
353
|
+
when you want your sorting to be case insensitive
|
354
|
+
-->
|
355
|
+
<filter class="solr.LowerCaseFilterFactory" />
|
356
|
+
<!-- The TrimFilter removes any leading or trailing whitespace -->
|
357
|
+
<filter class="solr.TrimFilterFactory" />
|
358
|
+
<!-- The PatternReplaceFilter gives you the flexibility to use
|
359
|
+
Java Regular expression to replace any sequence of characters
|
360
|
+
matching a pattern with an arbitrary replacement string,
|
361
|
+
which may include back references to portions of the original
|
362
|
+
string matched by the pattern.
|
363
|
+
|
364
|
+
See the Java Regular Expression documentation for more
|
365
|
+
information on pattern and replacement string syntax.
|
366
|
+
|
367
|
+
http://java.sun.com/j2se/1.5.0/docs/api/java/util/regex/package-summary.html
|
368
|
+
-->
|
369
|
+
<filter class="solr.PatternReplaceFilterFactory"
|
370
|
+
pattern="([^a-z])" replacement="" replace="all"
|
371
|
+
/>
|
372
|
+
</analyzer>
|
373
|
+
</fieldType>
|
374
|
+
|
375
|
+
<fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
|
376
|
+
<analyzer>
|
377
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
378
|
+
<filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
|
379
|
+
</analyzer>
|
380
|
+
</fieldtype>
|
381
|
+
|
382
|
+
<fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
|
383
|
+
<analyzer>
|
384
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
385
|
+
<!--
|
386
|
+
The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
|
387
|
+
a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
|
388
|
+
Attributes of the DelimitedPayloadTokenFilterFactory :
|
389
|
+
"delimiter" - a one character delimiter. Default is | (pipe)
|
390
|
+
"encoder" - how to encode the following value into a playload
|
391
|
+
float -> org.apache.lucene.analysis.payloads.FloatEncoder,
|
392
|
+
integer -> o.a.l.a.p.IntegerEncoder
|
393
|
+
identity -> o.a.l.a.p.IdentityEncoder
|
394
|
+
Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
|
395
|
+
-->
|
396
|
+
<filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
|
397
|
+
</analyzer>
|
398
|
+
</fieldtype>
|
399
|
+
|
400
|
+
<!-- lowercases the entire field value, keeping it as a single token. -->
|
401
|
+
<fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
|
402
|
+
<analyzer>
|
403
|
+
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
404
|
+
<filter class="solr.LowerCaseFilterFactory" />
|
405
|
+
</analyzer>
|
406
|
+
</fieldType>
|
407
|
+
|
408
|
+
<fieldType name="text_path" class="solr.TextField" positionIncrementGap="100">
|
409
|
+
<analyzer>
|
410
|
+
<tokenizer class="solr.PathHierarchyTokenizerFactory"/>
|
411
|
+
</analyzer>
|
412
|
+
</fieldType>
|
413
|
+
|
414
|
+
<!-- since fields of this type are by default not stored or indexed,
|
415
|
+
any data added to them will be ignored outright. -->
|
416
|
+
<fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
|
417
|
+
|
418
|
+
<!-- This point type indexes the coordinates as separate fields (subFields)
|
419
|
+
If subFieldType is defined, it references a type, and a dynamic field
|
420
|
+
definition is created matching *___<typename>. Alternately, if
|
421
|
+
subFieldSuffix is defined, that is used to create the subFields.
|
422
|
+
Example: if subFieldType="double", then the coordinates would be
|
423
|
+
indexed in fields myloc_0___double,myloc_1___double.
|
424
|
+
Example: if subFieldSuffix="_d" then the coordinates would be indexed
|
425
|
+
in fields myloc_0_d,myloc_1_d
|
426
|
+
The subFields are an implementation detail of the fieldType, and end
|
427
|
+
users normally should not need to know about them.
|
428
|
+
-->
|
429
|
+
<fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
|
430
|
+
|
431
|
+
<!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
|
432
|
+
<fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
|
433
|
+
|
434
|
+
<!--
|
435
|
+
A Geohash is a compact representation of a latitude longitude pair in a single field.
|
436
|
+
See http://wiki.apache.org/solr/SpatialSearch
|
437
|
+
-->
|
438
|
+
<fieldtype name="geohash" class="solr.GeoHashField"/>
|
439
|
+
</types>
|
440
|
+
|
441
|
+
|
442
|
+
<fields>
|
443
|
+
<field name="id" type="string" indexed="true" stored="true" required="true" />
|
444
|
+
<field name="type" type="string" indexed="true" stored="true" required="true" />
|
445
|
+
<field name="enabled" type="boolean" indexed="true" stored="true" multiValued="true" />
|
446
|
+
<field name="location" type="location" indexed="true" stored="true" />
|
447
|
+
<field name="user_id" type="int" indexed="true" stored="true" />
|
448
|
+
<field name="popularity" type="int" indexed="true" stored="true" />
|
449
|
+
<field name="text" type="text" indexed="true" stored="true" />
|
450
|
+
|
451
|
+
<dynamicField name="*_i" type="int" indexed="true" stored="true"/>
|
452
|
+
<dynamicField name="*_s" type="string" indexed="true" stored="true"/>
|
453
|
+
<dynamicField name="*_l" type="long" indexed="true" stored="true"/>
|
454
|
+
<dynamicField name="*_t" type="text" indexed="true" stored="true"/>
|
455
|
+
<dynamicField name="*_txt" type="text" indexed="true" stored="true" multiValued="true"/>
|
456
|
+
<dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
|
457
|
+
<dynamicField name="*_f" type="float" indexed="true" stored="true"/>
|
458
|
+
<dynamicField name="*_d" type="double" indexed="true" stored="true"/>
|
459
|
+
<dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
|
460
|
+
<dynamicField name="*_p" type="location" indexed="true" stored="true"/>
|
461
|
+
<dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
|
462
|
+
<dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
|
463
|
+
<dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
|
464
|
+
<dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
|
465
|
+
<dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
|
466
|
+
<dynamicField name="*_pi" type="pint" indexed="true" stored="true"/>
|
467
|
+
<dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false"/>
|
468
|
+
<dynamicField name="ignored_*" type="ignored" multiValued="true"/>
|
469
|
+
<dynamicField name="attr_*" type="textgen" indexed="true" stored="true" multiValued="true"/>
|
470
|
+
<dynamicField name="random_*" type="random" />
|
471
|
+
</fields>
|
472
|
+
<uniqueKey>id</uniqueKey>
|
473
|
+
<defaultSearchField>text</defaultSearchField>
|
474
|
+
<solrQueryParser defaultOperator="AND"/>
|
475
|
+
</schema>
|