1 |
28918
|
claudio.at
|
<?xml version="1.0" encoding="UTF-8" ?>
|
2 |
40659
|
sandro.lab
|
<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
|
3 |
46713
|
claudio.at
|
<xsl:output omit-xml-declaration="yes" indent="yes"/>
|
4 |
28918
|
claudio.at
|
|
5 |
46713
|
claudio.at
|
<xsl:template match="/FIELDS">
|
6 |
28918
|
claudio.at
|
|
7 |
46713
|
claudio.at
|
<xsl:param name="textFieldType" select="string('text_common')"/>
|
8 |
|
|
<xsl:variable name="smallcase" select="'abcdefghijklmnopqrstuvwxyz'"/>
|
9 |
|
|
<xsl:variable name="uppercase" select="'ABCDEFGHIJKLMNOPQRSTUVWXYZ'"/>
|
10 |
28918
|
claudio.at
|
|
11 |
46713
|
claudio.at
|
<!--
|
12 |
|
|
D-Net index schema template
|
13 |
28918
|
claudio.at
|
|
14 |
46713
|
claudio.at
|
CHANGELOG
|
15 |
28918
|
claudio.at
|
|
16 |
46713
|
claudio.at
|
0.1 : first release
|
17 |
|
|
0.2 : added preserveOriginal="1" for text field type in the index analyzer and catenateWords="1" for the query analyzer
|
18 |
|
|
0.3 : changed language for SnowballPorterFilterFactory to language="German2" (index/query) in the text field type
|
19 |
|
|
0.4 : added solr.ASCIIFoldingFilterFactory filter (index/query) in the text field type
|
20 |
|
|
0.5 : added long_keyword field type, to be used for objIdentifiers
|
21 |
|
|
0.6 : added field types for spellchecking
|
22 |
|
|
0.7 : added parameter for text field type
|
23 |
|
|
0.8 : added field _version_, needed by Solr 4.0.0 for the transaction log
|
24 |
|
|
0.9 : added type: text_en_splitting
|
25 |
|
|
0.91 : added type: ngramtext
|
26 |
|
|
0.92 : added schema optimizations, removing unnecessary stored fields
|
27 |
|
|
0.93 : added attribute preserveOriginal="1" to fieldtype ngramtext (query analysis) to improve matches
|
28 |
|
|
0.94 : updated and simplified ngramtext fieldtype
|
29 |
|
|
0.95 : update to solr 4.4, removed attribute "compress" from field definition, ngramfield doesn't support NGramFilterFactory anymore
|
30 |
|
|
0.96 : update to solr 4.9
|
31 |
46976
|
claudio.at
|
0.97 : introduced field type string_ci supporting case insensitivity.
|
32 |
53847
|
claudio.at
|
1.0 : updated to solr 6.6.0
|
33 |
46713
|
claudio.at
|
-->
|
34 |
53847
|
claudio.at
|
<schema name="dnet" version="1.0">
|
35 |
28918
|
claudio.at
|
|
36 |
53847
|
claudio.at
|
<!-- Valid attributes for fields:
|
37 |
|
|
name: mandatory - the name for the field
|
38 |
|
|
type: mandatory - the name of a field type from the
|
39 |
|
|
fieldTypes section
|
40 |
|
|
indexed: true if this field should be indexed (searchable or sortable)
|
41 |
|
|
stored: true if this field should be retrievable
|
42 |
|
|
docValues: true if this field should have doc values. Doc values are
|
43 |
|
|
useful (required, if you are using *Point fields) for faceting,
|
44 |
|
|
grouping, sorting and function queries. Doc values will make the index
|
45 |
|
|
faster to load, more NRT-friendly and more memory-efficient.
|
46 |
|
|
They however come with some limitations: they are currently only
|
47 |
|
|
supported by StrField, UUIDField, all Trie*Fields and *PointFields,
|
48 |
|
|
and depending on the field type, they might require the field to be
|
49 |
|
|
single-valued, be required or have a default value (check the
|
50 |
|
|
documentation of the field type you're interested in for more information)
|
51 |
|
|
multiValued: true if this field may contain multiple values per document
|
52 |
|
|
omitNorms: (expert) set to true to omit the norms associated with
|
53 |
|
|
this field (this disables length normalization and index-time
|
54 |
|
|
boosting for the field, and saves some memory). Only full-text
|
55 |
|
|
fields or fields that need an index-time boost need norms.
|
56 |
|
|
Norms are omitted for primitive (non-analyzed) types by default.
|
57 |
|
|
termVectors: [false] set to true to store the term vector for a
|
58 |
|
|
given field.
|
59 |
|
|
When using MoreLikeThis, fields used for similarity should be
|
60 |
|
|
stored for best performance.
|
61 |
|
|
termPositions: Store position information with the term vector.
|
62 |
|
|
This will increase storage costs.
|
63 |
|
|
termOffsets: Store offset information with the term vector. This
|
64 |
|
|
will increase storage costs.
|
65 |
|
|
required: The field is required. It will throw an error if the
|
66 |
|
|
value does not exist
|
67 |
|
|
default: a value that should be used if no value is specified
|
68 |
|
|
when adding a document.
|
69 |
|
|
-->
|
70 |
28918
|
claudio.at
|
|
71 |
53847
|
claudio.at
|
<!-- field names should consist of alphanumeric or underscore characters only and
|
72 |
|
|
not start with a digit. This is not currently strictly enforced,
|
73 |
|
|
but other field names will not have first class support from all components
|
74 |
|
|
and back compatibility is not guaranteed. Names with both leading and
|
75 |
|
|
trailing underscores (e.g. _version_) are reserved.
|
76 |
|
|
-->
|
77 |
28918
|
claudio.at
|
|
78 |
53847
|
claudio.at
|
<xsl:for-each select="./FIELD">
|
79 |
|
|
<xsl:variable name="fieldname" select="translate(@name, $uppercase, $smallcase)"/>
|
80 |
|
|
<xsl:variable name="fieldtype">
|
81 |
|
|
<xsl:choose>
|
82 |
|
|
<xsl:when test="@type"><xsl:value-of select="@type"/></xsl:when>
|
83 |
|
|
<!-- this comment is here as a reference,
|
84 |
|
|
once the MDFormat profile will be updated, remove the old type mappings
|
85 |
46715
|
claudio.at
|
|
86 |
53847
|
claudio.at
|
<xsl:when test="@type='int'">pint</xsl:when>
|
87 |
|
|
<xsl:when test="@type='date'">pdate</xsl:when>
|
88 |
|
|
<xsl:when test="@type='ngramtext'">ngramtext</xsl:when>
|
89 |
|
|
<xsl:when test="@type='string_ci'">string_ci</xsl:when>
|
90 |
|
|
-->
|
91 |
|
|
<xsl:when test="@tokenizable='false'">string</xsl:when>
|
92 |
|
|
<xsl:otherwise>
|
93 |
|
|
<xsl:value-of select="$textFieldType"/>
|
94 |
|
|
</xsl:otherwise>
|
95 |
|
|
</xsl:choose>
|
96 |
|
|
</xsl:variable>
|
97 |
|
|
<xsl:variable name="isMultivalued">
|
98 |
|
|
<xsl:choose>
|
99 |
|
|
<xsl:when test="@multivalued='false'">false</xsl:when>
|
100 |
|
|
<xsl:otherwise>true</xsl:otherwise>
|
101 |
|
|
</xsl:choose>
|
102 |
|
|
</xsl:variable>
|
103 |
|
|
<xsl:variable name="isStored">
|
104 |
|
|
<xsl:choose>
|
105 |
|
|
<xsl:when test="@stored='true'">true</xsl:when>
|
106 |
|
|
<xsl:otherwise>false</xsl:otherwise>
|
107 |
|
|
</xsl:choose>
|
108 |
|
|
</xsl:variable>
|
109 |
28918
|
claudio.at
|
|
110 |
53847
|
claudio.at
|
<field name="{$fieldname}" type="{$fieldtype}" indexed="{@indexable}" stored="{normalize-space($isStored)}" multiValued="{normalize-space($isMultivalued)}"/>
|
111 |
|
|
</xsl:for-each>
|
112 |
28918
|
claudio.at
|
|
113 |
53847
|
claudio.at
|
<field name="__indexrecordidentifier" type="string" indexed="true" stored="true" multiValued="false" required="true"/>
|
114 |
28918
|
claudio.at
|
|
115 |
53847
|
claudio.at
|
<field name="__deleted" type="boolean" indexed="true" stored="false" default="false" omitNorms="true" omitTermFreqAndPositions="true"/>
|
116 |
28918
|
claudio.at
|
|
117 |
53847
|
claudio.at
|
<field name="__dsid" type="string" indexed="true" stored="true" omitNorms="true" omitTermFreqAndPositions="true"/>
|
118 |
28918
|
claudio.at
|
|
119 |
53847
|
claudio.at
|
<field name="__dsversion" type="pdate" indexed="true" stored="true" omitNorms="true" omitTermFreqAndPositions="true"/>
|
120 |
28918
|
claudio.at
|
|
121 |
53847
|
claudio.at
|
<field name="__result" type="string" indexed="false" stored="true" multiValued="false" docValues="false"/>
|
122 |
28918
|
claudio.at
|
|
123 |
53847
|
claudio.at
|
<field name="__all" type="{$textFieldType}" indexed="true" stored="false" multiValued="true"/>
|
124 |
28918
|
claudio.at
|
|
125 |
53847
|
claudio.at
|
<field name="_version_" type="long" indexed="true" stored="true" multiValued="false" />
|
126 |
28918
|
claudio.at
|
|
127 |
53847
|
claudio.at
|
<field name="_root_" type="string" indexed="true" stored="false" docValues="false" />
|
128 |
28918
|
claudio.at
|
|
129 |
53847
|
claudio.at
|
<!-- field for ping -->
|
130 |
|
|
<field name="text" type="{$textFieldType}" indexed="false" stored="false"/>
|
131 |
28918
|
claudio.at
|
|
132 |
53847
|
claudio.at
|
<!-- Field to use to determine and enforce document uniqueness.
|
133 |
|
|
Unless this field is marked with required="false", it will be a required field
|
134 |
|
|
-->
|
135 |
|
|
<uniqueKey>__indexrecordidentifier</uniqueKey>
|
136 |
28918
|
claudio.at
|
|
137 |
53847
|
claudio.at
|
<xsl:for-each select="./FIELD[(@type = 'ngramtext' or not(@type)) and not(@tokenizable = 'false')]">
|
138 |
|
|
<xsl:variable name="fieldname" select="translate(@name, $uppercase, $smallcase)"/>
|
139 |
|
|
<copyField source="{$fieldname}" dest="__all"/>
|
140 |
|
|
</xsl:for-each>
|
141 |
28918
|
claudio.at
|
|
142 |
53847
|
claudio.at
|
<!-- copyField commands copy one field to another at the time a document
|
143 |
|
|
is added to the index. It's used either to index the same field differently,
|
144 |
|
|
or to add multiple fields to the same field for easier/faster searching.
|
145 |
28918
|
claudio.at
|
|
146 |
53847
|
claudio.at
|
<copyField source="sourceFieldName" dest="destinationFieldName"/>
|
147 |
|
|
-->
|
148 |
28918
|
claudio.at
|
|
149 |
53847
|
claudio.at
|
<!-- field type definitions. The "name" attribute is
|
150 |
|
|
just a label to be used by field definitions. The "class"
|
151 |
|
|
attribute and any other attributes determine the real
|
152 |
|
|
behavior of the fieldType.
|
153 |
|
|
Class names starting with "solr" refer to java classes in a
|
154 |
|
|
standard package such as org.apache.solr.analysis
|
155 |
|
|
-->
|
156 |
28918
|
claudio.at
|
|
157 |
53847
|
claudio.at
|
<!-- The StrField type is not analyzed, but indexed/stored verbatim.
|
158 |
|
|
It supports doc values but in that case the field needs to be
|
159 |
|
|
single-valued and either required or have a default value.
|
160 |
|
|
-->
|
161 |
|
|
<fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true" />
|
162 |
|
|
<fieldType name="strings" class="solr.StrField" sortMissingLast="true" multiValued="true" docValues="true" />
|
163 |
28918
|
claudio.at
|
|
164 |
53847
|
claudio.at
|
<!-- boolean type: "true" or "false" -->
|
165 |
|
|
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
|
166 |
28918
|
claudio.at
|
|
167 |
53847
|
claudio.at
|
<fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
|
168 |
28918
|
claudio.at
|
|
169 |
53847
|
claudio.at
|
<!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
|
170 |
|
|
currently supported on types that are sorted internally as strings
|
171 |
|
|
and on numeric types.
|
172 |
|
|
This includes "string","boolean", "int", "float", "long", "date", "double",
|
173 |
|
|
including the "Trie" and "Point" variants.
|
174 |
|
|
- If sortMissingLast="true", then a sort on this field will cause documents
|
175 |
|
|
without the field to come after documents with the field,
|
176 |
|
|
regardless of the requested sort order (asc or desc).
|
177 |
|
|
- If sortMissingFirst="true", then a sort on this field will cause documents
|
178 |
|
|
without the field to come before documents with the field,
|
179 |
|
|
regardless of the requested sort order.
|
180 |
|
|
- If sortMissingLast="false" and sortMissingFirst="false" (the default),
|
181 |
|
|
then default lucene sorting will be used which places docs without the
|
182 |
|
|
field first in an ascending sort and last in a descending sort.
|
183 |
|
|
-->
|
184 |
28918
|
claudio.at
|
|
185 |
53847
|
claudio.at
|
<!--
|
186 |
|
|
Numeric field types that index values using KD-trees. *Point fields are faster and more efficient than Trie* fields both, at
|
187 |
|
|
search time and at index time, but some features are still not supported.
|
188 |
|
|
Point fields don't support FieldCache, so they must have docValues="true" if needed for sorting, faceting, functions, etc.
|
189 |
|
|
-->
|
190 |
|
|
<fieldType name="pint" class="solr.IntPointField" docValues="true"/>
|
191 |
|
|
<fieldType name="pfloat" class="solr.FloatPointField" docValues="true"/>
|
192 |
|
|
<fieldType name="plong" class="solr.LongPointField" docValues="true"/>
|
193 |
|
|
<fieldType name="pdouble" class="solr.DoublePointField" docValues="true"/>
|
194 |
28918
|
claudio.at
|
|
195 |
53847
|
claudio.at
|
<fieldType name="pints" class="solr.IntPointField" docValues="true" multiValued="true"/>
|
196 |
|
|
<fieldType name="pfloats" class="solr.FloatPointField" docValues="true" multiValued="true"/>
|
197 |
|
|
<fieldType name="plongs" class="solr.LongPointField" docValues="true" multiValued="true"/>
|
198 |
|
|
<fieldType name="pdoubles" class="solr.DoublePointField" docValues="true" multiValued="true"/>
|
199 |
28918
|
claudio.at
|
|
200 |
53847
|
claudio.at
|
<!--
|
201 |
|
|
Default numeric field types. For faster range queries, consider *PointFields (pint/pfloat/plong/pdouble), or the
|
202 |
|
|
tint/tfloat/tlong/tdouble types.
|
203 |
|
|
-->
|
204 |
|
|
<fieldType name="int" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
|
205 |
|
|
<fieldType name="float" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
|
206 |
|
|
<fieldType name="long" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
|
207 |
|
|
<fieldType name="double" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
|
208 |
28918
|
claudio.at
|
|
209 |
53847
|
claudio.at
|
<fieldType name="ints" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
|
210 |
|
|
<fieldType name="floats" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
|
211 |
|
|
<fieldType name="longs" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
|
212 |
|
|
<fieldType name="doubles" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
|
213 |
28918
|
claudio.at
|
|
214 |
53847
|
claudio.at
|
<!--
|
215 |
|
|
Numeric field types that index each value at various levels of precision
|
216 |
|
|
to accelerate range queries when the number of values between the range
|
217 |
|
|
endpoints is large. See the javadoc for NumericRangeQuery for internal
|
218 |
|
|
implementation details.
|
219 |
28918
|
claudio.at
|
|
220 |
53847
|
claudio.at
|
Smaller precisionStep values (specified in bits) will lead to more tokens
|
221 |
|
|
indexed per value, slightly larger index size, and faster range queries.
|
222 |
|
|
A precisionStep of 0 disables indexing at different precision levels.
|
223 |
28918
|
claudio.at
|
|
224 |
53847
|
claudio.at
|
Consider using pint/pfloat/plong/pdouble instead of Trie* fields if possible
|
225 |
|
|
-->
|
226 |
|
|
<fieldType name="tint" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
|
227 |
|
|
<fieldType name="tfloat" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
|
228 |
|
|
<fieldType name="tlong" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
|
229 |
|
|
<fieldType name="tdouble" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
|
230 |
28918
|
claudio.at
|
|
231 |
53847
|
claudio.at
|
<fieldType name="tints" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
|
232 |
|
|
<fieldType name="tfloats" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
|
233 |
|
|
<fieldType name="tlongs" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
|
234 |
|
|
<fieldType name="tdoubles" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
|
235 |
28918
|
claudio.at
|
|
236 |
53847
|
claudio.at
|
<!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
|
237 |
|
|
is a more restricted form of the canonical representation of dateTime
|
238 |
|
|
http://www.w3.org/TR/xmlschema-2/#dateTime
|
239 |
|
|
The trailing "Z" designates UTC time and is mandatory.
|
240 |
|
|
Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
|
241 |
|
|
All other components are mandatory.
|
242 |
28918
|
claudio.at
|
|
243 |
53847
|
claudio.at
|
Expressions can also be used to denote calculations that should be
|
244 |
|
|
performed relative to "NOW" to determine the value, ie...
|
245 |
28918
|
claudio.at
|
|
246 |
53847
|
claudio.at
|
NOW/HOUR
|
247 |
|
|
... Round to the start of the current hour
|
248 |
|
|
NOW-1DAY
|
249 |
|
|
... Exactly 1 day prior to now
|
250 |
|
|
NOW/DAY+6MONTHS+3DAYS
|
251 |
|
|
... 6 months and 3 days in the future from the start of
|
252 |
|
|
the current day
|
253 |
28918
|
claudio.at
|
|
254 |
53847
|
claudio.at
|
Consult the TrieDateField javadocs for more information.
|
255 |
|
|
-->
|
256 |
|
|
<!-- KD-tree versions of date fields -->
|
257 |
|
|
<fieldType name="pdate" class="solr.DatePointField" docValues="true"/>
|
258 |
|
|
<fieldType name="pdates" class="solr.DatePointField" docValues="true" multiValued="true"/>
|
259 |
28918
|
claudio.at
|
|
260 |
53847
|
claudio.at
|
<fieldType name="date" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
|
261 |
|
|
<fieldType name="dates" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
|
262 |
|
|
|
263 |
|
|
<fieldType name="tdate" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0"/>
|
264 |
|
|
<fieldType name="tdates" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0" multiValued="true"/>
|
265 |
|
|
|
266 |
|
|
|
267 |
|
|
<!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
|
268 |
|
|
<fieldType name="binary" class="solr.BinaryField"/>
|
269 |
|
|
|
270 |
|
|
<!-- The "RandomSortField" is not used to store or search any
|
271 |
|
|
data. You can declare fields of this type it in your schema
|
272 |
|
|
to generate pseudo-random orderings of your docs for sorting
|
273 |
|
|
or function purposes. The ordering is generated based on the field
|
274 |
|
|
name and the version of the index. As long as the index version
|
275 |
|
|
remains unchanged, and the same field name is reused,
|
276 |
|
|
the ordering of the docs will be consistent.
|
277 |
|
|
If you want different psuedo-random orderings of documents,
|
278 |
|
|
for the same version of the index, use a dynamicField and
|
279 |
|
|
change the field name in the request.
|
280 |
|
|
-->
|
281 |
|
|
<fieldType name="random" class="solr.RandomSortField" indexed="true" />
|
282 |
|
|
|
283 |
|
|
<!-- solr.TextField allows the specification of custom text analyzers
|
284 |
|
|
specified as a tokenizer and a list of token filters. Different
|
285 |
|
|
analyzers may be specified for indexing and querying.
|
286 |
|
|
|
287 |
|
|
The optional positionIncrementGap puts space between multiple fields of
|
288 |
|
|
this type on the same document, with the purpose of preventing false phrase
|
289 |
|
|
matching across fields.
|
290 |
|
|
|
291 |
|
|
For more info on customizing your analyzer chain, please see
|
292 |
|
|
http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
|
293 |
|
|
-->
|
294 |
|
|
|
295 |
|
|
<!-- One can also specify an existing Analyzer class that has a
|
296 |
|
|
default constructor via the class attribute on the analyzer element.
|
297 |
|
|
Example:
|
298 |
|
|
<fieldType name="text_greek" class="solr.TextField">
|
299 |
|
|
<analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
|
300 |
|
|
</fieldType>
|
301 |
|
|
-->
|
302 |
|
|
|
303 |
|
|
<!-- A text field that only splits on whitespace for exact matching of words -->
|
304 |
|
|
<!-- <dynamicField name="*_ws" type="text_ws" indexed="true" stored="true"/> -->
|
305 |
|
|
|
306 |
|
|
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
|
307 |
|
|
<analyzer>
|
308 |
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
309 |
|
|
</analyzer>
|
310 |
|
|
</fieldType>
|
311 |
|
|
|
312 |
|
|
<fieldType name="ngramtext" class="solr.TextField">
|
313 |
|
|
<analyzer type="index">
|
314 |
|
|
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
315 |
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
316 |
|
|
<filter class="solr.NGramFilterFactory" minGramSize="3" maxGramSize="25"/>
|
317 |
|
|
<filter class="solr.TrimFilterFactory"/>
|
318 |
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
319 |
|
|
</analyzer>
|
320 |
|
|
<analyzer type="query">
|
321 |
|
|
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
322 |
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
323 |
|
|
</analyzer>
|
324 |
|
|
</fieldType>
|
325 |
|
|
|
326 |
|
|
|
327 |
|
|
<fieldType name="personName" class="solr.TextField" positionIncrementGap="100">
|
328 |
|
|
<analyzer>
|
329 |
|
|
<tokenizer class="solr.StandardTokenizerFactory" />
|
330 |
|
|
<filter class="solr.LowerCaseFilterFactory" />
|
331 |
|
|
</analyzer>
|
332 |
|
|
</fieldType>
|
333 |
|
|
|
334 |
|
|
<fieldType name="personNamePrefix" class="solr.TextField" positionIncrementGap="100">
|
335 |
|
|
<analyzer type="index">
|
336 |
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
337 |
|
|
<filter class="solr.LowerCaseFilterFactory" />
|
338 |
|
|
<filter class="solr.NGramFilterFactory" minGramSize="1" maxGramSize="30" />
|
339 |
|
|
</analyzer>
|
340 |
|
|
<analyzer type="query">
|
341 |
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
342 |
|
|
<filter class="solr.LowerCaseFilterFactory" />
|
343 |
|
|
</analyzer>
|
344 |
|
|
</fieldType>
|
345 |
|
|
|
346 |
|
|
|
347 |
|
|
<!-- A general text field that has reasonable, generic
|
348 |
|
|
cross-language defaults: it tokenizes with StandardTokenizer,
|
349 |
|
|
removes stop words from case-insensitive "stopwords.txt"
|
350 |
|
|
(empty by default), and down cases. At query time only, it
|
351 |
|
|
also applies synonyms.
|
352 |
46713
|
claudio.at
|
-->
|
353 |
53847
|
claudio.at
|
<fieldType name="text_common" class="solr.TextField" positionIncrementGap="100" multiValued="true">
|
354 |
|
|
<analyzer type="index">
|
355 |
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
356 |
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
|
357 |
|
|
<!-- in this example, we will only use synonyms at query time
|
358 |
|
|
<filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
|
359 |
|
|
<filter class="solr.FlattenGraphFilterFactory"/>
|
360 |
|
|
-->
|
361 |
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
362 |
|
|
</analyzer>
|
363 |
|
|
<analyzer type="query">
|
364 |
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
365 |
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
|
366 |
|
|
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
367 |
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
368 |
|
|
</analyzer>
|
369 |
|
|
</fieldType>
|
370 |
28918
|
claudio.at
|
|
371 |
53847
|
claudio.at
|
<!-- A text field with defaults appropriate for English: it
|
372 |
|
|
tokenizes with StandardTokenizer, removes English stop words
|
373 |
|
|
(stopwords_en.txt), down cases, protects words from protwords.txt, and
|
374 |
|
|
finally applies Porter's stemming. The query time analyzer
|
375 |
|
|
also applies synonyms from synonyms.txt. -->
|
376 |
|
|
<!-- <dynamicField name="*_txt_en" type="text_en" indexed="true" stored="true"/> -->
|
377 |
28918
|
claudio.at
|
|
378 |
53847
|
claudio.at
|
<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
|
379 |
|
|
<analyzer type="index">
|
380 |
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
381 |
|
|
<!-- in this example, we will only use synonyms at query time
|
382 |
|
|
<filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
|
383 |
|
|
<filter class="solr.FlattenGraphFilterFactory"/>
|
384 |
|
|
-->
|
385 |
|
|
<!-- Case insensitive stop word removal.
|
386 |
|
|
-->
|
387 |
|
|
<filter class="solr.StopFilterFactory"
|
388 |
|
|
ignoreCase="true"
|
389 |
|
|
words="stopwords.txt"
|
390 |
|
|
/>
|
391 |
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
392 |
|
|
<filter class="solr.EnglishPossessiveFilterFactory"/>
|
393 |
|
|
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
394 |
|
|
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
|
395 |
|
|
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
396 |
|
|
-->
|
397 |
|
|
<filter class="solr.PorterStemFilterFactory"/>
|
398 |
|
|
</analyzer>
|
399 |
|
|
<analyzer type="query">
|
400 |
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
401 |
|
|
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
402 |
|
|
<filter class="solr.StopFilterFactory"
|
403 |
|
|
ignoreCase="true"
|
404 |
|
|
words="stopwords.txt"
|
405 |
|
|
/>
|
406 |
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
407 |
|
|
<filter class="solr.EnglishPossessiveFilterFactory"/>
|
408 |
|
|
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
409 |
|
|
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
|
410 |
|
|
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
411 |
|
|
-->
|
412 |
|
|
<filter class="solr.PorterStemFilterFactory"/>
|
413 |
|
|
</analyzer>
|
414 |
|
|
</fieldType>
|
415 |
28918
|
claudio.at
|
|
416 |
53847
|
claudio.at
|
<!-- A text field with defaults appropriate for English, plus
|
417 |
|
|
aggressive word-splitting and autophrase features enabled.
|
418 |
|
|
This field is just like text_en, except it adds
|
419 |
|
|
WordDelimiterGraphFilter to enable splitting and matching of
|
420 |
|
|
words on case-change, alpha numeric boundaries, and
|
421 |
|
|
non-alphanumeric chars. This means certain compound word
|
422 |
|
|
cases will work, for example query "wi fi" will match
|
423 |
|
|
document "WiFi" or "wi-fi".
|
424 |
|
|
-->
|
425 |
|
|
<!-- <dynamicField name="*_txt_en_split" type="text_en_splitting" indexed="true" stored="true"/> -->
|
426 |
|
|
<fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
|
427 |
|
|
<analyzer type="index">
|
428 |
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
429 |
|
|
<!-- in this example, we will only use synonyms at query time
|
430 |
|
|
<filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
|
431 |
|
|
-->
|
432 |
|
|
<!-- Case insensitive stop word removal.
|
433 |
|
|
-->
|
434 |
|
|
<filter class="solr.StopFilterFactory"
|
435 |
|
|
ignoreCase="true"
|
436 |
|
|
words="stopwords.txt"
|
437 |
|
|
/>
|
438 |
|
|
<filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
|
439 |
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
440 |
|
|
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
441 |
|
|
<filter class="solr.PorterStemFilterFactory"/>
|
442 |
|
|
<filter class="solr.FlattenGraphFilterFactory" />
|
443 |
|
|
</analyzer>
|
444 |
|
|
<analyzer type="query">
|
445 |
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
446 |
|
|
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
447 |
|
|
<filter class="solr.StopFilterFactory"
|
448 |
|
|
ignoreCase="true"
|
449 |
|
|
words="stopwords.txt"
|
450 |
|
|
/>
|
451 |
|
|
<filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
|
452 |
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
453 |
|
|
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
454 |
|
|
<filter class="solr.PorterStemFilterFactory"/>
|
455 |
|
|
</analyzer>
|
456 |
|
|
</fieldType>
|
457 |
28918
|
claudio.at
|
|
458 |
53847
|
claudio.at
|
<!-- Less flexible matching, but less false matches. Probably not ideal for product names,
|
459 |
|
|
but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
|
460 |
|
|
<!-- <dynamicField name="*_txt_en_split_tight" type="text_en_splitting_tight" indexed="true" stored="true"/> -->
|
461 |
|
|
<fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
|
462 |
|
|
<analyzer type="index">
|
463 |
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
464 |
|
|
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
|
465 |
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
|
466 |
|
|
<filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
|
467 |
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
468 |
|
|
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
469 |
|
|
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
470 |
|
|
<!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
|
471 |
|
|
possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
|
472 |
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
473 |
|
|
<filter class="solr.FlattenGraphFilterFactory" />
|
474 |
|
|
</analyzer>
|
475 |
|
|
<analyzer type="query">
|
476 |
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
477 |
|
|
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
|
478 |
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
|
479 |
|
|
<filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
|
480 |
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
481 |
|
|
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
482 |
|
|
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
483 |
|
|
<!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
|
484 |
|
|
possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
|
485 |
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
486 |
|
|
</analyzer>
|
487 |
|
|
</fieldType>
|
488 |
|
|
|
489 |
|
|
<!-- Just like text_common except it reverses the characters of
|
490 |
|
|
each token, to enable more efficient leading wildcard queries.
|
491 |
|
|
-->
|
492 |
|
|
<!-- <dynamicField name="*_txt_rev" type="text_common_rev" indexed="true" stored="true"/> -->
|
493 |
|
|
<fieldType name="text_rev" class="solr.TextField" positionIncrementGap="100">
|
494 |
|
|
<analyzer type="index">
|
495 |
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
496 |
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
|
497 |
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
498 |
|
|
<filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
|
499 |
|
|
maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
|
500 |
|
|
</analyzer>
|
501 |
|
|
<analyzer type="query">
|
502 |
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
503 |
|
|
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
504 |
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
|
505 |
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
506 |
|
|
</analyzer>
|
507 |
|
|
</fieldType>
|
508 |
|
|
|
509 |
|
|
<!-- <dynamicField name="*_phon_en" type="phonetic_en" indexed="true" stored="true"/> -->
|
510 |
|
|
<fieldType name="phonetic_en" stored="false" indexed="true" class="solr.TextField" >
|
511 |
|
|
<analyzer>
|
512 |
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
513 |
|
|
<filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
|
514 |
|
|
</analyzer>
|
515 |
|
|
</fieldType>
|
516 |
|
|
|
517 |
|
|
<fieldType name="string_ci" class="solr.TextField" sortMissingLast="true" omitNorms="true">
|
518 |
|
|
<analyzer type="query">
|
519 |
|
|
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
520 |
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
521 |
|
|
</analyzer>
|
522 |
|
|
</fieldType>
|
523 |
|
|
|
524 |
|
|
<!--
|
525 |
|
|
Example of using PathHierarchyTokenizerFactory at index time, so
|
526 |
|
|
queries for paths match documents at that path, or in descendent paths
|
527 |
|
|
-->
|
528 |
|
|
<!-- <dynamicField name="*_descendent_path" type="descendent_path" indexed="true" stored="true"/> -->
|
529 |
|
|
<fieldType name="descendent_path" class="solr.TextField">
|
530 |
|
|
<analyzer type="index">
|
531 |
|
|
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
|
532 |
|
|
</analyzer>
|
533 |
|
|
<analyzer type="query">
|
534 |
|
|
<tokenizer class="solr.KeywordTokenizerFactory" />
|
535 |
|
|
</analyzer>
|
536 |
|
|
</fieldType>
|
537 |
|
|
|
538 |
|
|
<!--
|
539 |
|
|
Example of using PathHierarchyTokenizerFactory at query time, so
|
540 |
|
|
queries for paths match documents at that path, or in ancestor paths
|
541 |
|
|
-->
|
542 |
|
|
<!-- <dynamicField name="*_ancestor_path" type="ancestor_path" indexed="true" stored="true"/> -->
|
543 |
|
|
<fieldType name="ancestor_path" class="solr.TextField">
|
544 |
|
|
<analyzer type="index">
|
545 |
|
|
<tokenizer class="solr.KeywordTokenizerFactory" />
|
546 |
|
|
</analyzer>
|
547 |
|
|
<analyzer type="query">
|
548 |
|
|
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
|
549 |
|
|
</analyzer>
|
550 |
|
|
</fieldType>
|
551 |
|
|
|
552 |
|
|
<!-- since fields of this type are by default not stored or indexed,
|
553 |
|
|
any data added to them will be ignored outright. -->
|
554 |
|
|
<fieldType name="ignored" stored="false" indexed="false" docValues="false" multiValued="true" class="solr.StrField" />
|
555 |
|
|
|
556 |
|
|
<!-- This point type indexes the coordinates as separate fields (subFields)
|
557 |
|
|
If subFieldType is defined, it references a type, and a dynamic field
|
558 |
|
|
definition is created matching *___<typename>. Alternately, if
|
559 |
|
|
subFieldSuffix is defined, that is used to create the subFields.
|
560 |
|
|
Example: if subFieldType="double", then the coordinates would be
|
561 |
|
|
indexed in fields myloc_0___double,myloc_1___double.
|
562 |
|
|
Example: if subFieldSuffix="_d" then the coordinates would be indexed
|
563 |
|
|
in fields myloc_0_d,myloc_1_d
|
564 |
|
|
The subFields are an implementation detail of the fieldType, and end
|
565 |
|
|
users normally should not need to know about them.
|
566 |
|
|
-->
|
567 |
|
|
<!-- <dynamicField name="*_point" type="point" indexed="true" stored="true"/> -->
|
568 |
|
|
<fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
|
569 |
|
|
|
570 |
|
|
<!-- A specialized field for geospatial search filters and distance sorting. -->
|
571 |
|
|
<fieldType name="location" class="solr.LatLonPointSpatialField" docValues="true"/>
|
572 |
|
|
|
573 |
|
|
<!-- An alternative geospatial field type new to Solr 4. It supports multiValued and polygon shapes.
|
574 |
|
|
For more information about this and other Spatial fields new to Solr 4, see:
|
575 |
|
|
http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
|
576 |
|
|
-->
|
577 |
|
|
<fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
|
578 |
|
|
geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
|
579 |
|
|
|
580 |
46713
|
claudio.at
|
</schema>
|
581 |
|
|
</xsl:template>
|
582 |
53847
|
claudio.at
|
</xsl:stylesheet>
|