1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
|
<?xml version="1.0" encoding="UTF-8" ?>
<!--
Licensed to the Apache Software Foundation (ASF) under one or more
contributor license agreements. See the NOTICE file distributed with
this work for additional information regarding copyright ownership.
The ASF licenses this file to You under the Apache License, Version 2.0
(the "License"); you may not use this file except in compliance with
the License. You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
-->
<schema name="example-DIH-atom" version="1.6">
<uniqueKey>id</uniqueKey>
<field name="id" type="string" indexed="true" stored="true" required="true"/>
<field name="title" type="text_en_splitting" indexed="true" stored="true"/>
<field name="author" type="string" indexed="true" stored="true"/>
<field name="category" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="link" type="string" indexed="true" stored="true"/>
<field name="summary" type="text_en_splitting" indexed="true" stored="true"/>
<field name="rank" type="pint" indexed="true" stored="true"/>
<dynamicField name="*_dt" type="pdate" indexed="true" stored="true"/>
<!-- Catch-all field, aggregating all "useful to search as text" fields via the copyField instructions -->
<field name="text" type="text_en_splitting" indexed="true" stored="false" multiValued="true"/>
<field name="urls" type="url_only" indexed="true" stored="false"/>
<copyField source="id" dest="text"/>
<copyField source="title" dest="text"/>
<copyField source="author" dest="text"/>
<copyField source="category" dest="text"/>
<copyField source="summary" dest="text"/>
<!-- extract URLs from summary for faceting -->
<copyField source="summary" dest="urls"/>
<fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true"/>
<fieldType name="pint" class="solr.IntPointField" docValues="true"/>
<fieldType name="pdate" class="solr.DatePointField" docValues="true"/>
<!-- A text field with defaults appropriate for English, plus
aggressive word-splitting and autophrase features enabled.
This field is just like text_en, except it adds
WordDelimiterFilter to enable splitting and matching of
words on case-change, alpha numeric boundaries, and
non-alphanumeric chars. This means certain compound word
cases will work, for example query "wi fi" will match
document "WiFi" or "wi-fi".
-->
<fieldType name="text_en_splitting" class="solr.TextField"
positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-->
<!-- Case insensitive stop word removal. -->
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1"
catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
<filter class="solr.FlattenGraphFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1"
catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
</fieldType>
<!-- Field type that extracts URLs from the text.
As the stored representation is not changed, it is only useful for faceting.
It is not terribly useful for searching URLs either, as there are too many special symbols.
-->
<fieldType name="url_only" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.UAX29URLEmailTokenizerFactory" maxTokenLength="255"/>
<filter class="solr.TypeTokenFilterFactory" types="url_types.txt" useWhitelist="true"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.KeywordTokenizerFactory"/>
</analyzer>
</fieldType>
</schema>
|
