solrsrv 1.0.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.document +5 -0
- data/.gitignore +11 -0
- data/LICENSE +20 -0
- data/README.md +27 -0
- data/Rakefile +28 -0
- data/VERSION +1 -0
- data/apache-solr-1.4.0/README.txt +42 -0
- data/apache-solr-1.4.0/etc/jetty.xml +212 -0
- data/apache-solr-1.4.0/etc/webdefault.xml +379 -0
- data/apache-solr-1.4.0/example-DIH/README.txt +43 -0
- data/apache-solr-1.4.0/example-DIH/hsqldb/ex.backup +0 -0
- data/apache-solr-1.4.0/example-DIH/hsqldb/ex.data +0 -0
- data/apache-solr-1.4.0/example-DIH/hsqldb/ex.log +2 -0
- data/apache-solr-1.4.0/example-DIH/hsqldb/ex.properties +17 -0
- data/apache-solr-1.4.0/example-DIH/hsqldb/ex.script +12 -0
- data/apache-solr-1.4.0/example-DIH/solr/db/conf/admin-extra.html +31 -0
- data/apache-solr-1.4.0/example-DIH/solr/db/conf/db-data-config.xml +31 -0
- data/apache-solr-1.4.0/example-DIH/solr/db/conf/elevate.xml +36 -0
- data/apache-solr-1.4.0/example-DIH/solr/db/conf/protwords.txt +21 -0
- data/apache-solr-1.4.0/example-DIH/solr/db/conf/schema.xml +356 -0
- data/apache-solr-1.4.0/example-DIH/solr/db/conf/scripts.conf +24 -0
- data/apache-solr-1.4.0/example-DIH/solr/db/conf/solrconfig.xml +705 -0
- data/apache-solr-1.4.0/example-DIH/solr/db/conf/stopwords.txt +58 -0
- data/apache-solr-1.4.0/example-DIH/solr/db/conf/synonyms.txt +31 -0
- data/apache-solr-1.4.0/example-DIH/solr/db/conf/xslt/example.xsl +132 -0
- data/apache-solr-1.4.0/example-DIH/solr/db/conf/xslt/example_atom.xsl +63 -0
- data/apache-solr-1.4.0/example-DIH/solr/db/conf/xslt/example_rss.xsl +62 -0
- data/apache-solr-1.4.0/example-DIH/solr/db/conf/xslt/luke.xsl +345 -0
- data/apache-solr-1.4.0/example-DIH/solr/db/lib/hsqldb-1.8.0.10.jar +0 -0
- data/apache-solr-1.4.0/example-DIH/solr/mail/conf/data-config.xml +11 -0
- data/apache-solr-1.4.0/example-DIH/solr/mail/conf/protwords.txt +21 -0
- data/apache-solr-1.4.0/example-DIH/solr/mail/conf/schema.xml +370 -0
- data/apache-solr-1.4.0/example-DIH/solr/mail/conf/solrconfig.xml +807 -0
- data/apache-solr-1.4.0/example-DIH/solr/mail/conf/stopwords.txt +58 -0
- data/apache-solr-1.4.0/example-DIH/solr/mail/conf/synonyms.txt +31 -0
- data/apache-solr-1.4.0/example-DIH/solr/rss/conf/admin-extra.html +31 -0
- data/apache-solr-1.4.0/example-DIH/solr/rss/conf/elevate.xml +36 -0
- data/apache-solr-1.4.0/example-DIH/solr/rss/conf/protwords.txt +21 -0
- data/apache-solr-1.4.0/example-DIH/solr/rss/conf/rss-data-config.xml +26 -0
- data/apache-solr-1.4.0/example-DIH/solr/rss/conf/schema.xml +316 -0
- data/apache-solr-1.4.0/example-DIH/solr/rss/conf/scripts.conf +24 -0
- data/apache-solr-1.4.0/example-DIH/solr/rss/conf/solrconfig.xml +704 -0
- data/apache-solr-1.4.0/example-DIH/solr/rss/conf/stopwords.txt +58 -0
- data/apache-solr-1.4.0/example-DIH/solr/rss/conf/synonyms.txt +31 -0
- data/apache-solr-1.4.0/example-DIH/solr/solr.xml +8 -0
- data/apache-solr-1.4.0/exampledocs/books.csv +11 -0
- data/apache-solr-1.4.0/exampledocs/hd.xml +48 -0
- data/apache-solr-1.4.0/exampledocs/ipod_other.xml +52 -0
- data/apache-solr-1.4.0/exampledocs/ipod_video.xml +36 -0
- data/apache-solr-1.4.0/exampledocs/mem.xml +60 -0
- data/apache-solr-1.4.0/exampledocs/monitor.xml +31 -0
- data/apache-solr-1.4.0/exampledocs/monitor2.xml +30 -0
- data/apache-solr-1.4.0/exampledocs/mp500.xml +39 -0
- data/apache-solr-1.4.0/exampledocs/payload.xml +57 -0
- data/apache-solr-1.4.0/exampledocs/post.jar +0 -0
- data/apache-solr-1.4.0/exampledocs/post.sh +28 -0
- data/apache-solr-1.4.0/exampledocs/sd500.xml +34 -0
- data/apache-solr-1.4.0/exampledocs/solr.xml +38 -0
- data/apache-solr-1.4.0/exampledocs/test_utf8.sh +83 -0
- data/apache-solr-1.4.0/exampledocs/utf8-example.xml +42 -0
- data/apache-solr-1.4.0/exampledocs/vidcard.xml +54 -0
- data/apache-solr-1.4.0/lib/jetty-6.1.3.jar +0 -0
- data/apache-solr-1.4.0/lib/jetty-util-6.1.3.jar +0 -0
- data/apache-solr-1.4.0/lib/jsp-2.1/ant-1.6.5.jar +0 -0
- data/apache-solr-1.4.0/lib/jsp-2.1/core-3.1.1.jar +0 -0
- data/apache-solr-1.4.0/lib/jsp-2.1/jsp-2.1.jar +0 -0
- data/apache-solr-1.4.0/lib/jsp-2.1/jsp-api-2.1.jar +0 -0
- data/apache-solr-1.4.0/lib/servlet-api-2.5-6.1.3.jar +0 -0
- data/apache-solr-1.4.0/logs/.gitkeep +0 -0
- data/apache-solr-1.4.0/multicore/README.txt +3 -0
- data/apache-solr-1.4.0/multicore/core0/conf/schema.xml +41 -0
- data/apache-solr-1.4.0/multicore/core0/conf/solrconfig.xml +40 -0
- data/apache-solr-1.4.0/multicore/core1/conf/schema.xml +41 -0
- data/apache-solr-1.4.0/multicore/core1/conf/solrconfig.xml +40 -0
- data/apache-solr-1.4.0/multicore/exampledocs/ipod_other.xml +34 -0
- data/apache-solr-1.4.0/multicore/exampledocs/ipod_video.xml +22 -0
- data/apache-solr-1.4.0/multicore/solr.xml +35 -0
- data/apache-solr-1.4.0/solr/README.txt +54 -0
- data/apache-solr-1.4.0/solr/conf/admin-extra.html +31 -0
- data/apache-solr-1.4.0/solr/conf/elevate.xml +36 -0
- data/apache-solr-1.4.0/solr/conf/mapping-ISOLatin1Accent.txt +246 -0
- data/apache-solr-1.4.0/solr/conf/protwords.txt +21 -0
- data/apache-solr-1.4.0/solr/conf/schema.xml +569 -0
- data/apache-solr-1.4.0/solr/conf/scripts.conf +24 -0
- data/apache-solr-1.4.0/solr/conf/solrconfig.xml +1033 -0
- data/apache-solr-1.4.0/solr/conf/spellings.txt +2 -0
- data/apache-solr-1.4.0/solr/conf/stopwords.txt +58 -0
- data/apache-solr-1.4.0/solr/conf/synonyms.txt +31 -0
- data/apache-solr-1.4.0/solr/conf/xslt/example.xsl +132 -0
- data/apache-solr-1.4.0/solr/conf/xslt/example_atom.xsl +67 -0
- data/apache-solr-1.4.0/solr/conf/xslt/example_rss.xsl +66 -0
- data/apache-solr-1.4.0/solr/conf/xslt/luke.xsl +337 -0
- data/apache-solr-1.4.0/start.jar +0 -0
- data/apache-solr-1.4.0/webapps/solr.war +0 -0
- data/bin/solrsrv +39 -0
- data/lib/generators/solrsrv/update_config/templates/solrsrv.yml +17 -0
- data/lib/generators/solrsrv/update_config/update_config_generator.rb +17 -0
- data/lib/solrsrv/engine.rb +6 -0
- data/lib/solrsrv.rb +5 -0
- data/lib/tasks/solrsrv.rake +49 -0
- data/solrsrv.gemspec +143 -0
- metadata +184 -0
@@ -0,0 +1,569 @@
|
|
1
|
+
<?xml version="1.0" encoding="UTF-8" ?>
|
2
|
+
<!--
|
3
|
+
Licensed to the Apache Software Foundation (ASF) under one or more
|
4
|
+
contributor license agreements. See the NOTICE file distributed with
|
5
|
+
this work for additional information regarding copyright ownership.
|
6
|
+
The ASF licenses this file to You under the Apache License, Version 2.0
|
7
|
+
(the "License"); you may not use this file except in compliance with
|
8
|
+
the License. You may obtain a copy of the License at
|
9
|
+
|
10
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
11
|
+
|
12
|
+
Unless required by applicable law or agreed to in writing, software
|
13
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
14
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
15
|
+
See the License for the specific language governing permissions and
|
16
|
+
limitations under the License.
|
17
|
+
-->
|
18
|
+
|
19
|
+
<!--
|
20
|
+
This is the Solr schema file. This file should be named "schema.xml" and
|
21
|
+
should be in the conf directory under the solr home
|
22
|
+
(i.e. ./solr/conf/schema.xml by default)
|
23
|
+
or located where the classloader for the Solr webapp can find it.
|
24
|
+
|
25
|
+
This example schema is the recommended starting point for users.
|
26
|
+
It should be kept correct and concise, usable out-of-the-box.
|
27
|
+
|
28
|
+
For more information, on how to customize this file, please see
|
29
|
+
http://wiki.apache.org/solr/SchemaXml
|
30
|
+
|
31
|
+
PERFORMANCE NOTE: this schema includes many optional features and should not
|
32
|
+
be used for benchmarking. To improve performance one could
|
33
|
+
- set stored="false" for all fields possible (esp large fields) when you
|
34
|
+
only need to search on the field but don't need to return the original
|
35
|
+
value.
|
36
|
+
- set indexed="false" if you don't need to search on the field, but only
|
37
|
+
return the field as a result of searching on other indexed fields.
|
38
|
+
- remove all unneeded copyField statements
|
39
|
+
- for best index size and searching performance, set "index" to false
|
40
|
+
for all general text fields, use copyField to copy them to the
|
41
|
+
catchall "text" field, and use that for searching.
|
42
|
+
- For maximum indexing performance, use the StreamingUpdateSolrServer
|
43
|
+
java client.
|
44
|
+
- Remember to run the JVM in server mode, and use a higher logging level
|
45
|
+
that avoids logging every request
|
46
|
+
-->
|
47
|
+
|
48
|
+
<schema name="example" version="1.2">
|
49
|
+
<!-- attribute "name" is the name of this schema and is only used for display purposes.
|
50
|
+
Applications should change this to reflect the nature of the search collection.
|
51
|
+
version="1.2" is Solr's version number for the schema syntax and semantics. It should
|
52
|
+
not normally be changed by applications.
|
53
|
+
1.0: multiValued attribute did not exist, all fields are multiValued by nature
|
54
|
+
1.1: multiValued attribute introduced, false by default
|
55
|
+
1.2: omitTermFreqAndPositions attribute introduced, true by default except for text fields.
|
56
|
+
-->
|
57
|
+
|
58
|
+
<types>
|
59
|
+
<!-- field type definitions. The "name" attribute is
|
60
|
+
just a label to be used by field definitions. The "class"
|
61
|
+
attribute and any other attributes determine the real
|
62
|
+
behavior of the fieldType.
|
63
|
+
Class names starting with "solr" refer to java classes in the
|
64
|
+
org.apache.solr.analysis package.
|
65
|
+
-->
|
66
|
+
|
67
|
+
<!-- The StrField type is not analyzed, but indexed/stored verbatim.
|
68
|
+
- StrField and TextField support an optional compressThreshold which
|
69
|
+
limits compression (if enabled in the derived fields) to values which
|
70
|
+
exceed a certain size (in characters).
|
71
|
+
-->
|
72
|
+
<fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
|
73
|
+
|
74
|
+
<!-- boolean type: "true" or "false" -->
|
75
|
+
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
|
76
|
+
<!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
|
77
|
+
<fieldtype name="binary" class="solr.BinaryField"/>
|
78
|
+
|
79
|
+
<!-- The optional sortMissingLast and sortMissingFirst attributes are
|
80
|
+
currently supported on types that are sorted internally as strings.
|
81
|
+
This includes "string","boolean","sint","slong","sfloat","sdouble","pdate"
|
82
|
+
- If sortMissingLast="true", then a sort on this field will cause documents
|
83
|
+
without the field to come after documents with the field,
|
84
|
+
regardless of the requested sort order (asc or desc).
|
85
|
+
- If sortMissingFirst="true", then a sort on this field will cause documents
|
86
|
+
without the field to come before documents with the field,
|
87
|
+
regardless of the requested sort order.
|
88
|
+
- If sortMissingLast="false" and sortMissingFirst="false" (the default),
|
89
|
+
then default lucene sorting will be used which places docs without the
|
90
|
+
field first in an ascending sort and last in a descending sort.
|
91
|
+
-->
|
92
|
+
|
93
|
+
<!--
|
94
|
+
Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
|
95
|
+
-->
|
96
|
+
<fieldType name="int" class="solr.TrieIntField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
|
97
|
+
<fieldType name="float" class="solr.TrieFloatField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
|
98
|
+
<fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
|
99
|
+
<fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
|
100
|
+
|
101
|
+
<!--
|
102
|
+
Numeric field types that index each value at various levels of precision
|
103
|
+
to accelerate range queries when the number of values between the range
|
104
|
+
endpoints is large. See the javadoc for NumericRangeQuery for internal
|
105
|
+
implementation details.
|
106
|
+
|
107
|
+
Smaller precisionStep values (specified in bits) will lead to more tokens
|
108
|
+
indexed per value, slightly larger index size, and faster range queries.
|
109
|
+
A precisionStep of 0 disables indexing at different precision levels.
|
110
|
+
-->
|
111
|
+
<fieldType name="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
|
112
|
+
<fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
|
113
|
+
<fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
|
114
|
+
<fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
|
115
|
+
|
116
|
+
<!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
|
117
|
+
is a more restricted form of the canonical representation of dateTime
|
118
|
+
http://www.w3.org/TR/xmlschema-2/#dateTime
|
119
|
+
The trailing "Z" designates UTC time and is mandatory.
|
120
|
+
Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
|
121
|
+
All other components are mandatory.
|
122
|
+
|
123
|
+
Expressions can also be used to denote calculations that should be
|
124
|
+
performed relative to "NOW" to determine the value, ie...
|
125
|
+
|
126
|
+
NOW/HOUR
|
127
|
+
... Round to the start of the current hour
|
128
|
+
NOW-1DAY
|
129
|
+
... Exactly 1 day prior to now
|
130
|
+
NOW/DAY+6MONTHS+3DAYS
|
131
|
+
... 6 months and 3 days in the future from the start of
|
132
|
+
the current day
|
133
|
+
|
134
|
+
Consult the DateField javadocs for more information.
|
135
|
+
|
136
|
+
Note: For faster range queries, consider the tdate type
|
137
|
+
-->
|
138
|
+
<fieldType name="date" class="solr.TrieDateField" omitNorms="true" precisionStep="0" positionIncrementGap="0"/>
|
139
|
+
|
140
|
+
<!-- A Trie based date field for faster date range queries and date faceting. -->
|
141
|
+
<fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" precisionStep="6" positionIncrementGap="0"/>
|
142
|
+
|
143
|
+
|
144
|
+
<!--
|
145
|
+
Note:
|
146
|
+
These should only be used for compatibility with existing indexes (created with older Solr versions)
|
147
|
+
or if "sortMissingFirst" or "sortMissingLast" functionality is needed. Use Trie based fields instead.
|
148
|
+
|
149
|
+
Plain numeric field types that store and index the text
|
150
|
+
value verbatim (and hence don't support range queries, since the
|
151
|
+
lexicographic ordering isn't equal to the numeric ordering)
|
152
|
+
-->
|
153
|
+
<fieldType name="pint" class="solr.IntField" omitNorms="true"/>
|
154
|
+
<fieldType name="plong" class="solr.LongField" omitNorms="true"/>
|
155
|
+
<fieldType name="pfloat" class="solr.FloatField" omitNorms="true"/>
|
156
|
+
<fieldType name="pdouble" class="solr.DoubleField" omitNorms="true"/>
|
157
|
+
<fieldType name="pdate" class="solr.DateField" sortMissingLast="true" omitNorms="true"/>
|
158
|
+
|
159
|
+
|
160
|
+
<!--
|
161
|
+
Note:
|
162
|
+
These should only be used for compatibility with existing indexes (created with older Solr versions)
|
163
|
+
or if "sortMissingFirst" or "sortMissingLast" functionality is needed. Use Trie based fields instead.
|
164
|
+
|
165
|
+
Numeric field types that manipulate the value into
|
166
|
+
a string value that isn't human-readable in its internal form,
|
167
|
+
but with a lexicographic ordering the same as the numeric ordering,
|
168
|
+
so that range queries work correctly.
|
169
|
+
-->
|
170
|
+
<fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/>
|
171
|
+
<fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/>
|
172
|
+
<fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/>
|
173
|
+
<fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/>
|
174
|
+
|
175
|
+
|
176
|
+
<!-- The "RandomSortField" is not used to store or search any
|
177
|
+
data. You can declare fields of this type it in your schema
|
178
|
+
to generate pseudo-random orderings of your docs for sorting
|
179
|
+
purposes. The ordering is generated based on the field name
|
180
|
+
and the version of the index, As long as the index version
|
181
|
+
remains unchanged, and the same field name is reused,
|
182
|
+
the ordering of the docs will be consistent.
|
183
|
+
If you want different psuedo-random orderings of documents,
|
184
|
+
for the same version of the index, use a dynamicField and
|
185
|
+
change the name
|
186
|
+
-->
|
187
|
+
<fieldType name="random" class="solr.RandomSortField" indexed="true" />
|
188
|
+
|
189
|
+
<!-- solr.TextField allows the specification of custom text analyzers
|
190
|
+
specified as a tokenizer and a list of token filters. Different
|
191
|
+
analyzers may be specified for indexing and querying.
|
192
|
+
|
193
|
+
The optional positionIncrementGap puts space between multiple fields of
|
194
|
+
this type on the same document, with the purpose of preventing false phrase
|
195
|
+
matching across fields.
|
196
|
+
|
197
|
+
For more info on customizing your analyzer chain, please see
|
198
|
+
http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
|
199
|
+
-->
|
200
|
+
|
201
|
+
<!-- One can also specify an existing Analyzer class that has a
|
202
|
+
default constructor via the class attribute on the analyzer element
|
203
|
+
<fieldType name="text_greek" class="solr.TextField">
|
204
|
+
<analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
|
205
|
+
</fieldType>
|
206
|
+
-->
|
207
|
+
|
208
|
+
<!-- A text field that only splits on whitespace for exact matching of words -->
|
209
|
+
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
|
210
|
+
<analyzer>
|
211
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
212
|
+
</analyzer>
|
213
|
+
</fieldType>
|
214
|
+
|
215
|
+
<!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
|
216
|
+
words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
|
217
|
+
so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
|
218
|
+
Synonyms and stopwords are customized by external files, and stemming is enabled.
|
219
|
+
-->
|
220
|
+
<fieldType name="text" class="solr.TextField" positionIncrementGap="100">
|
221
|
+
<analyzer type="index">
|
222
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
223
|
+
<!-- in this example, we will only use synonyms at query time
|
224
|
+
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
|
225
|
+
-->
|
226
|
+
<!-- Case insensitive stop word removal.
|
227
|
+
add enablePositionIncrements=true in both the index and query
|
228
|
+
analyzers to leave a 'gap' for more accurate phrase queries.
|
229
|
+
-->
|
230
|
+
<filter class="solr.StopFilterFactory"
|
231
|
+
ignoreCase="true"
|
232
|
+
words="stopwords.txt"
|
233
|
+
enablePositionIncrements="true"
|
234
|
+
/>
|
235
|
+
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
|
236
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
237
|
+
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
|
238
|
+
</analyzer>
|
239
|
+
<analyzer type="query">
|
240
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
241
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
242
|
+
<filter class="solr.StopFilterFactory"
|
243
|
+
ignoreCase="true"
|
244
|
+
words="stopwords.txt"
|
245
|
+
enablePositionIncrements="true"
|
246
|
+
/>
|
247
|
+
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
|
248
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
249
|
+
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
|
250
|
+
</analyzer>
|
251
|
+
</fieldType>
|
252
|
+
|
253
|
+
|
254
|
+
<!-- Less flexible matching, but less false matches. Probably not ideal for product names,
|
255
|
+
but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
|
256
|
+
<fieldType name="textTight" class="solr.TextField" positionIncrementGap="100" >
|
257
|
+
<analyzer>
|
258
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
259
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
|
260
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
|
261
|
+
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
|
262
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
263
|
+
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
|
264
|
+
<!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
|
265
|
+
possible with WordDelimiterFilter in conjuncton with stemming. -->
|
266
|
+
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
267
|
+
</analyzer>
|
268
|
+
</fieldType>
|
269
|
+
|
270
|
+
|
271
|
+
<!-- A general unstemmed text field - good if one does not know the language of the field -->
|
272
|
+
<fieldType name="textgen" class="solr.TextField" positionIncrementGap="100">
|
273
|
+
<analyzer type="index">
|
274
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
275
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
|
276
|
+
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
|
277
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
278
|
+
</analyzer>
|
279
|
+
<analyzer type="query">
|
280
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
281
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
282
|
+
<filter class="solr.StopFilterFactory"
|
283
|
+
ignoreCase="true"
|
284
|
+
words="stopwords.txt"
|
285
|
+
enablePositionIncrements="true"
|
286
|
+
/>
|
287
|
+
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
|
288
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
289
|
+
</analyzer>
|
290
|
+
</fieldType>
|
291
|
+
|
292
|
+
|
293
|
+
<!-- A general unstemmed text field that indexes tokens normally and also
|
294
|
+
reversed (via ReversedWildcardFilterFactory), to enable more efficient
|
295
|
+
leading wildcard queries. -->
|
296
|
+
<fieldType name="text_rev" class="solr.TextField" positionIncrementGap="100">
|
297
|
+
<analyzer type="index">
|
298
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
299
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
|
300
|
+
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
|
301
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
302
|
+
<filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
|
303
|
+
maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
|
304
|
+
</analyzer>
|
305
|
+
<analyzer type="query">
|
306
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
307
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
308
|
+
<filter class="solr.StopFilterFactory"
|
309
|
+
ignoreCase="true"
|
310
|
+
words="stopwords.txt"
|
311
|
+
enablePositionIncrements="true"
|
312
|
+
/>
|
313
|
+
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
|
314
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
315
|
+
</analyzer>
|
316
|
+
</fieldType>
|
317
|
+
|
318
|
+
<!-- charFilter + WhitespaceTokenizer -->
|
319
|
+
<!--
|
320
|
+
<fieldType name="textCharNorm" class="solr.TextField" positionIncrementGap="100" >
|
321
|
+
<analyzer>
|
322
|
+
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
|
323
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
324
|
+
</analyzer>
|
325
|
+
</fieldType>
|
326
|
+
-->
|
327
|
+
|
328
|
+
<!-- This is an example of using the KeywordTokenizer along
|
329
|
+
With various TokenFilterFactories to produce a sortable field
|
330
|
+
that does not include some properties of the source text
|
331
|
+
-->
|
332
|
+
<fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
|
333
|
+
<analyzer>
|
334
|
+
<!-- KeywordTokenizer does no actual tokenizing, so the entire
|
335
|
+
input string is preserved as a single token
|
336
|
+
-->
|
337
|
+
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
338
|
+
<!-- The LowerCase TokenFilter does what you expect, which can be
|
339
|
+
when you want your sorting to be case insensitive
|
340
|
+
-->
|
341
|
+
<filter class="solr.LowerCaseFilterFactory" />
|
342
|
+
<!-- The TrimFilter removes any leading or trailing whitespace -->
|
343
|
+
<filter class="solr.TrimFilterFactory" />
|
344
|
+
<!-- The PatternReplaceFilter gives you the flexibility to use
|
345
|
+
Java Regular expression to replace any sequence of characters
|
346
|
+
matching a pattern with an arbitrary replacement string,
|
347
|
+
which may include back references to portions of the original
|
348
|
+
string matched by the pattern.
|
349
|
+
|
350
|
+
See the Java Regular Expression documentation for more
|
351
|
+
information on pattern and replacement string syntax.
|
352
|
+
|
353
|
+
http://java.sun.com/j2se/1.5.0/docs/api/java/util/regex/package-summary.html
|
354
|
+
-->
|
355
|
+
<filter class="solr.PatternReplaceFilterFactory"
|
356
|
+
pattern="([^a-z])" replacement="" replace="all"
|
357
|
+
/>
|
358
|
+
</analyzer>
|
359
|
+
</fieldType>
|
360
|
+
|
361
|
+
<fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
|
362
|
+
<analyzer>
|
363
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
364
|
+
<filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
|
365
|
+
</analyzer>
|
366
|
+
</fieldtype>
|
367
|
+
|
368
|
+
<fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
|
369
|
+
<analyzer>
|
370
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
371
|
+
<!--
|
372
|
+
The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
|
373
|
+
a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
|
374
|
+
Attributes of the DelimitedPayloadTokenFilterFactory :
|
375
|
+
"delimiter" - a one character delimiter. Default is | (pipe)
|
376
|
+
"encoder" - how to encode the following value into a playload
|
377
|
+
float -> org.apache.lucene.analysis.payloads.FloatEncoder,
|
378
|
+
integer -> o.a.l.a.p.IntegerEncoder
|
379
|
+
identity -> o.a.l.a.p.IdentityEncoder
|
380
|
+
Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
|
381
|
+
-->
|
382
|
+
<filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
|
383
|
+
</analyzer>
|
384
|
+
</fieldtype>
|
385
|
+
|
386
|
+
<!-- lowercases the entire field value, keeping it as a single token. -->
|
387
|
+
<fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
|
388
|
+
<analyzer>
|
389
|
+
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
390
|
+
<filter class="solr.LowerCaseFilterFactory" />
|
391
|
+
</analyzer>
|
392
|
+
</fieldType>
|
393
|
+
|
394
|
+
|
395
|
+
<!-- since fields of this type are by default not stored or indexed,
|
396
|
+
any data added to them will be ignored outright. -->
|
397
|
+
<fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
|
398
|
+
|
399
|
+
</types>
|
400
|
+
|
401
|
+
|
402
|
+
<fields>
|
403
|
+
<!-- Valid attributes for fields:
|
404
|
+
name: mandatory - the name for the field
|
405
|
+
type: mandatory - the name of a previously defined type from the
|
406
|
+
<types> section
|
407
|
+
indexed: true if this field should be indexed (searchable or sortable)
|
408
|
+
stored: true if this field should be retrievable
|
409
|
+
compressed: [false] if this field should be stored using gzip compression
|
410
|
+
(this will only apply if the field type is compressable; among
|
411
|
+
the standard field types, only TextField and StrField are)
|
412
|
+
multiValued: true if this field may contain multiple values per document
|
413
|
+
omitNorms: (expert) set to true to omit the norms associated with
|
414
|
+
this field (this disables length normalization and index-time
|
415
|
+
boosting for the field, and saves some memory). Only full-text
|
416
|
+
fields or fields that need an index-time boost need norms.
|
417
|
+
termVectors: [false] set to true to store the term vector for a
|
418
|
+
given field.
|
419
|
+
When using MoreLikeThis, fields used for similarity should be
|
420
|
+
stored for best performance.
|
421
|
+
termPositions: Store position information with the term vector.
|
422
|
+
This will increase storage costs.
|
423
|
+
termOffsets: Store offset information with the term vector. This
|
424
|
+
will increase storage costs.
|
425
|
+
default: a value that should be used if no value is specified
|
426
|
+
when adding a document.
|
427
|
+
-->
|
428
|
+
|
429
|
+
<field name="id" type="string" indexed="true" stored="true" required="true" />
|
430
|
+
<field name="sku" type="textTight" indexed="true" stored="true" omitNorms="true"/>
|
431
|
+
<field name="name" type="textgen" indexed="true" stored="true"/>
|
432
|
+
<field name="alphaNameSort" type="alphaOnlySort" indexed="true" stored="false"/>
|
433
|
+
<field name="manu" type="textgen" indexed="true" stored="true" omitNorms="true"/>
|
434
|
+
<field name="cat" type="text_ws" indexed="true" stored="true" multiValued="true" omitNorms="true" />
|
435
|
+
<field name="features" type="text" indexed="true" stored="true" multiValued="true"/>
|
436
|
+
<field name="includes" type="text" indexed="true" stored="true" termVectors="true" termPositions="true" termOffsets="true" />
|
437
|
+
|
438
|
+
<field name="weight" type="float" indexed="true" stored="true"/>
|
439
|
+
<field name="price" type="float" indexed="true" stored="true"/>
|
440
|
+
<field name="popularity" type="int" indexed="true" stored="true" />
|
441
|
+
<field name="inStock" type="boolean" indexed="true" stored="true" />
|
442
|
+
|
443
|
+
|
444
|
+
<!-- Common metadata fields, named specifically to match up with
|
445
|
+
SolrCell metadata when parsing rich documents such as Word, PDF.
|
446
|
+
Some fields are multiValued only because Tika currently may return
|
447
|
+
multiple values for them.
|
448
|
+
-->
|
449
|
+
<field name="title" type="text" indexed="true" stored="true" multiValued="true"/>
|
450
|
+
<field name="subject" type="text" indexed="true" stored="true"/>
|
451
|
+
<field name="description" type="text" indexed="true" stored="true"/>
|
452
|
+
<field name="comments" type="text" indexed="true" stored="true"/>
|
453
|
+
<field name="author" type="textgen" indexed="true" stored="true"/>
|
454
|
+
<field name="keywords" type="textgen" indexed="true" stored="true"/>
|
455
|
+
<field name="category" type="textgen" indexed="true" stored="true"/>
|
456
|
+
<field name="content_type" type="string" indexed="true" stored="true" multiValued="true"/>
|
457
|
+
<field name="last_modified" type="date" indexed="true" stored="true"/>
|
458
|
+
<field name="links" type="string" indexed="true" stored="true" multiValued="true"/>
|
459
|
+
|
460
|
+
|
461
|
+
<!-- catchall field, containing all other searchable text fields (implemented
|
462
|
+
via copyField further on in this schema -->
|
463
|
+
<field name="text" type="text" indexed="true" stored="false" multiValued="true"/>
|
464
|
+
|
465
|
+
<!-- catchall text field that indexes tokens both normally and in reverse for efficient
|
466
|
+
leading wildcard queries. -->
|
467
|
+
<field name="text_rev" type="text_rev" indexed="true" stored="false" multiValued="true"/>
|
468
|
+
|
469
|
+
<!-- non-tokenized version of manufacturer to make it easier to sort or group
|
470
|
+
results by manufacturer. copied from "manu" via copyField -->
|
471
|
+
<field name="manu_exact" type="string" indexed="true" stored="false"/>
|
472
|
+
|
473
|
+
<field name="payloads" type="payloads" indexed="true" stored="true"/>
|
474
|
+
|
475
|
+
<!-- Uncommenting the following will create a "timestamp" field using
|
476
|
+
a default value of "NOW" to indicate when each document was indexed.
|
477
|
+
-->
|
478
|
+
<!--
|
479
|
+
<field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
|
480
|
+
-->
|
481
|
+
|
482
|
+
|
483
|
+
<!-- Dynamic field definitions. If a field name is not found, dynamicFields
|
484
|
+
will be used if the name matches any of the patterns.
|
485
|
+
RESTRICTION: the glob-like pattern in the name attribute must have
|
486
|
+
a "*" only at the start or the end.
|
487
|
+
EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
|
488
|
+
Longer patterns will be matched first. if equal size patterns
|
489
|
+
both match, the first appearing in the schema will be used. -->
|
490
|
+
<dynamicField name="*_i" type="int" indexed="true" stored="true"/>
|
491
|
+
<dynamicField name="*_s" type="string" indexed="true" stored="true"/>
|
492
|
+
<dynamicField name="*_l" type="long" indexed="true" stored="true"/>
|
493
|
+
<dynamicField name="*_t" type="text" indexed="true" stored="true"/>
|
494
|
+
<dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
|
495
|
+
<dynamicField name="*_f" type="float" indexed="true" stored="true"/>
|
496
|
+
<dynamicField name="*_d" type="double" indexed="true" stored="true"/>
|
497
|
+
<dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
|
498
|
+
|
499
|
+
<!-- some trie-coded dynamic fields for faster range queries -->
|
500
|
+
<dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
|
501
|
+
<dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
|
502
|
+
<dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
|
503
|
+
<dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
|
504
|
+
<dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
|
505
|
+
|
506
|
+
<dynamicField name="*_pi" type="pint" indexed="true" stored="true"/>
|
507
|
+
|
508
|
+
<dynamicField name="ignored_*" type="ignored" multiValued="true"/>
|
509
|
+
<dynamicField name="attr_*" type="textgen" indexed="true" stored="true" multiValued="true"/>
|
510
|
+
|
511
|
+
<dynamicField name="random_*" type="random" />
|
512
|
+
|
513
|
+
<!-- uncomment the following to ignore any fields that don't already match an existing
|
514
|
+
field name or dynamic field, rather than reporting them as an error.
|
515
|
+
alternately, change the type="ignored" to some other type e.g. "text" if you want
|
516
|
+
unknown fields indexed and/or stored by default -->
|
517
|
+
<!--dynamicField name="*" type="ignored" multiValued="true" /-->
|
518
|
+
|
519
|
+
</fields>
|
520
|
+
|
521
|
+
<!-- Field to use to determine and enforce document uniqueness.
|
522
|
+
Unless this field is marked with required="false", it will be a required field
|
523
|
+
-->
|
524
|
+
<uniqueKey>id</uniqueKey>
|
525
|
+
|
526
|
+
<!-- field for the QueryParser to use when an explicit fieldname is absent -->
|
527
|
+
<defaultSearchField>text</defaultSearchField>
|
528
|
+
|
529
|
+
<!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
|
530
|
+
<solrQueryParser defaultOperator="OR"/>
|
531
|
+
|
532
|
+
<!-- copyField commands copy one field to another at the time a document
|
533
|
+
is added to the index. It's used either to index the same field differently,
|
534
|
+
or to add multiple fields to the same field for easier/faster searching. -->
|
535
|
+
|
536
|
+
<copyField source="cat" dest="text"/>
|
537
|
+
<copyField source="name" dest="text"/>
|
538
|
+
<copyField source="manu" dest="text"/>
|
539
|
+
<copyField source="features" dest="text"/>
|
540
|
+
<copyField source="includes" dest="text"/>
|
541
|
+
<copyField source="manu" dest="manu_exact"/>
|
542
|
+
|
543
|
+
<!-- Above, multiple source fields are copied to the [text] field.
|
544
|
+
Another way to map multiple source fields to the same
|
545
|
+
destination field is to use the dynamic field syntax.
|
546
|
+
copyField also supports a maxChars to copy setting. -->
|
547
|
+
|
548
|
+
<!-- <copyField source="*_t" dest="text" maxChars="3000"/> -->
|
549
|
+
|
550
|
+
<!-- copy name to alphaNameSort, a field designed for sorting by name -->
|
551
|
+
<!-- <copyField source="name" dest="alphaNameSort"/> -->
|
552
|
+
|
553
|
+
|
554
|
+
<!-- Similarity is the scoring routine for each document vs. a query.
|
555
|
+
A custom similarity may be specified here, but the default is fine
|
556
|
+
for most applications. -->
|
557
|
+
<!-- <similarity class="org.apache.lucene.search.DefaultSimilarity"/> -->
|
558
|
+
<!-- ... OR ...
|
559
|
+
Specify a SimilarityFactory class name implementation
|
560
|
+
allowing parameters to be used.
|
561
|
+
-->
|
562
|
+
<!--
|
563
|
+
<similarity class="com.example.solr.CustomSimilarityFactory">
|
564
|
+
<str name="paramkey">param value</str>
|
565
|
+
</similarity>
|
566
|
+
-->
|
567
|
+
|
568
|
+
|
569
|
+
</schema>
|
@@ -0,0 +1,24 @@
|
|
1
|
+
# Licensed to the Apache Software Foundation (ASF) under one or more
|
2
|
+
# contributor license agreements. See the NOTICE file distributed with
|
3
|
+
# this work for additional information regarding copyright ownership.
|
4
|
+
# The ASF licenses this file to You under the Apache License, Version 2.0
|
5
|
+
# (the "License"); you may not use this file except in compliance with
|
6
|
+
# the License. You may obtain a copy of the License at
|
7
|
+
#
|
8
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
9
|
+
#
|
10
|
+
# Unless required by applicable law or agreed to in writing, software
|
11
|
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
12
|
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
13
|
+
# See the License for the specific language governing permissions and
|
14
|
+
# limitations under the License.
|
15
|
+
|
16
|
+
user=
|
17
|
+
solr_hostname=localhost
|
18
|
+
solr_port=8983
|
19
|
+
rsyncd_port=18983
|
20
|
+
data_dir=
|
21
|
+
webapp_name=solr
|
22
|
+
master_host=
|
23
|
+
master_data_dir=
|
24
|
+
master_status_dir=
|