1
<?xml version="1.0" encoding="UTF-8" ?>
2
<!-- $Id: schema.xml,v 1.1.2.1.2.33 2009/07/29 18:17:13 pwolanin Exp $ -->
5
This is the Solr schema file. This file should be named "schema.xml" and
6
should be in the conf directory under the solr home
7
(i.e. ./solr/conf/schema.xml by default)
8
or located where the classloader for the Solr webapp can find it.
10
For more information, on how to customize this file, please see
11
http://wiki.apache.org/solr/SchemaXml
14
<schema name="drupal-0.9.3" version="1.1">
15
<!-- attribute "name" is the name of this schema and is only used for display purposes.
16
Applications should change this to reflect the nature of the search collection.
17
version="1.1" is Solr's version number for the schema syntax and semantics. It should
18
not normally be changed by applications.
19
1.0: multiValued attribute did not exist, all fields are multiValued by nature
20
1.1: multiValued attribute introduced, false by default -->
23
<!-- field type definitions. The "name" attribute is
24
just a label to be used by field definitions. The "class"
25
attribute and any other attributes determine the real
26
behavior of the fieldType.
27
Class names starting with "solr" refer to java classes in the
28
org.apache.solr.analysis package.
31
<!-- The StrField type is not analyzed, but indexed/stored verbatim.
32
- StrField and TextField support an optional compressThreshold which
33
limits compression (if enabled in the derived fields) to values which
34
exceed a certain size (in characters).
36
<fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
38
<!-- boolean type: "true" or "false" -->
39
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
41
<!-- The optional sortMissingLast and sortMissingFirst attributes are
42
currently supported on types that are sorted internally as strings.
43
- If sortMissingLast="true", then a sort on this field will cause documents
44
without the field to come after documents with the field,
45
regardless of the requested sort order (asc or desc).
46
- If sortMissingFirst="true", then a sort on this field will cause documents
47
without the field to come before documents with the field,
48
regardless of the requested sort order.
49
- If sortMissingLast="false" and sortMissingFirst="false" (the default),
50
then default lucene sorting will be used which places docs without the
51
field first in an ascending sort and last in a descending sort.
55
<!-- numeric field types that store and index the text
56
value verbatim (and hence don't support range queries, since the
57
lexicographic ordering isn't equal to the numeric ordering) -->
58
<fieldType name="integer" class="solr.IntField" omitNorms="true"/>
59
<fieldType name="long" class="solr.LongField" omitNorms="true"/>
60
<fieldType name="float" class="solr.FloatField" omitNorms="true"/>
61
<fieldType name="double" class="solr.DoubleField" omitNorms="true"/>
64
<!-- Numeric field types that manipulate the value into
65
a string value that isn't human-readable in its internal form,
66
but with a lexicographic ordering the same as the numeric ordering,
67
so that range queries work correctly. -->
68
<fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/>
69
<fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/>
70
<fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/>
71
<fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/>
74
<!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
75
is a more restricted form of the canonical representation of dateTime
76
http://www.w3.org/TR/xmlschema-2/#dateTime
77
The trailing "Z" designates UTC time and is mandatory.
78
Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
79
All other components are mandatory.
81
Expressions can also be used to denote calculations that should be
82
performed relative to "NOW" to determine the value, ie...
85
... Round to the start of the current hour
87
... Exactly 1 day prior to now
89
... 6 months and 3 days in the future from the start of
92
Consult the DateField javadocs for more information.
94
<fieldType name="date" class="solr.DateField" sortMissingLast="true" omitNorms="true"/>
96
<!-- solr.TextField allows the specification of custom text analyzers
97
specified as a tokenizer and a list of token filters. Different
98
analyzers may be specified for indexing and querying.
100
The optional positionIncrementGap puts space between multiple fields of
101
this type on the same document, with the purpose of preventing false phrase
102
matching across fields.
104
For more info on customizing your analyzer chain, please see
105
http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
108
<!-- One can also specify an existing Analyzer class that has a
109
default constructor via the class attribute on the analyzer element
110
<fieldType name="text_greek" class="solr.TextField">
111
<analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
115
<!-- A text field that only splits on whitespace for exact matching of words -->
116
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
118
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
122
<!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
123
words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
124
so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
125
Synonyms and stopwords are customized by external files, and stemming is enabled.
126
Duplicate tokens at the same position (which may result from Stemmed Synonyms or
127
WordDelim parts) are removed.
129
<fieldType name="text" class="solr.TextField" positionIncrementGap="100">
130
<analyzer type="index">
131
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
132
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
133
<!-- in this example, we will only use synonyms at query time
134
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
136
<!-- Case insensitive stop word removal.
137
add enablePositionIncrements=true in both the index and query
138
analyzers to leave a 'gap' for more accurate phrase queries.
140
<filter class="solr.StopFilterFactory"
142
words="stopwords.txt"
143
enablePositionIncrements="true"
145
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
146
<filter class="solr.LowerCaseFilterFactory"/>
147
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
148
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
150
<analyzer type="query">
151
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
152
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
153
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
154
<filter class="solr.StopFilterFactory"
156
words="stopwords.txt"
157
enablePositionIncrements="true"
159
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
160
<filter class="solr.LowerCaseFilterFactory"/>
161
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
162
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
167
<!-- Less flexible matching, but less false matches. Probably not ideal for product names,
168
but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
169
<fieldType name="textTight" class="solr.TextField" positionIncrementGap="100" >
171
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
172
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
173
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
174
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
175
<filter class="solr.LowerCaseFilterFactory"/>
176
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
177
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
181
<!-- Setup simple analysis for spell checking -->
183
<fieldType name="textSpell" class="solr.TextField" positionIncrementGap="100">
185
<tokenizer class="solr.StandardTokenizerFactory" />
186
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
187
<filter class="solr.LengthFilterFactory" min="4" max="20" />
188
<filter class="solr.LowerCaseFilterFactory" />
189
<filter class="solr.RemoveDuplicatesTokenFilterFactory" />
193
<!-- This is an example of using the KeywordTokenizer along
194
With various TokenFilterFactories to produce a sortable field
195
that does not include some properties of the source text
197
<fieldType name="sortString" class="solr.TextField" sortMissingLast="true" omitNorms="true">
199
<!-- KeywordTokenizer does no actual tokenizing, so the entire
200
input string is preserved as a single token
202
<tokenizer class="solr.KeywordTokenizerFactory"/>
203
<!-- The LowerCase TokenFilter does what you expect, which can be
204
when you want your sorting to be case insensitive
206
<filter class="solr.LowerCaseFilterFactory" />
207
<!-- The TrimFilter removes any leading or trailing whitespace -->
208
<filter class="solr.TrimFilterFactory" />
209
<!-- The PatternReplaceFilter gives you the flexibility to use
210
Java Regular expression to replace any sequence of characters
211
matching a pattern with an arbitrary replacement string,
212
which may include back refrences to portions of the orriginal
213
string matched by the pattern.
215
See the Java Regular Expression documentation for more
216
infomation on pattern and replacement string syntax.
218
http://java.sun.com/j2se/1.5.0/docs/api/java/util/regex/package-summary.html
220
<filter class="solr.PatternReplaceFilterFactory"
221
pattern="(^\p{Punct}+)" replacement="" replace="all"
227
<!-- since fields of this type are by default not stored or indexed, any data added to
228
them will be ignored outright
230
<fieldtype name="ignored" stored="false" indexed="false" class="solr.StrField" />
236
<!-- Valid attributes for fields:
237
name: mandatory - the name for the field
238
type: mandatory - the name of a previously defined type from the <types> section
239
indexed: true if this field should be indexed (searchable or sortable)
240
stored: true if this field should be retrievable
241
compressed: [false] if this field should be stored using gzip compression
242
(this will only apply if the field type is compressable; among
243
the standard field types, only TextField and StrField are)
244
multiValued: true if this field may contain multiple values per document
245
omitNorms: (expert) set to true to omit the norms associated with
246
this field (this disables length normalization and index-time
247
boosting for the field, and saves some memory). Only full-text
248
fields or fields that need an index-time boost need norms.
251
<!-- The document id is derived from a site-spcific key (hash) and the node ID like:
252
$document->id = $hash . '/node/' . $node->nid; -->
254
<field name="id" type="string" indexed="true" stored="true" required="true" />
256
<!-- These are the fields that correspond to a Drupal node. The beauty of having
257
Lucene store title, body, type, etc., is that we retrieve them with the search
258
result set and don't need to go to the database with a node_load. -->
260
<field name="site" type="string" indexed="true" stored="true"/>
261
<field name="hash" type="string" indexed="true" stored="true"/>
262
<field name="url" type="string" indexed="true" stored="true"/>
263
<field name="title" type="text" indexed="true" stored="true" termVectors="true" omitNorms="true"/>
264
<field name="sort_title" type="sortString" indexed="true" stored="false"/>
265
<field name="body" type="text" indexed="true" stored="true" termVectors="true"/>
266
<field name="teaser" type="text" indexed="false" stored="true"/>
267
<field name="type" type="string" indexed="true" stored="true"/>
268
<field name="type_name" type="string" indexed="true" stored="true"/>
269
<field name="path" type="string" indexed="true" stored="true"/>
270
<field name="path_alias" type="text" indexed="true" stored="true" termVectors="true"/>
271
<field name="uid" type="integer" indexed="true" stored="true"/>
272
<field name="name" type="text" indexed="true" stored="true" termVectors="true"/>
273
<field name="sname" type="string" indexed="true" stored="false"/>
274
<field name="sort_name" type="sortString" indexed="true" stored="false"/>
275
<field name="created" type="date" indexed="true" stored="true"/>
276
<field name="changed" type="date" indexed="true" stored="true"/>
277
<field name="last_comment_or_change" type="date" indexed="true" stored="true"/>
278
<field name="nid" type="integer" indexed="true" stored="true"/>
279
<field name="status" type="boolean" indexed="true" stored="true"/>
280
<field name="promote" type="boolean" indexed="true" stored="true"/>
281
<field name="moderate" type="boolean" indexed="true" stored="true"/>
282
<field name="sticky" type="boolean" indexed="true" stored="true"/>
283
<field name="tnid" type="integer" indexed="true" stored="true"/>
284
<field name="translate" type="boolean" indexed="true" stored="true"/>
285
<field name="language" type="string" indexed="true" stored="true"/>
286
<field name="comment_count" type="integer" indexed="true" stored="true"/>
287
<field name="tid" type="integer" indexed="true" stored="true" multiValued="true"/>
288
<field name="vid" type="integer" indexed="true" stored="true" multiValued="true"/>
289
<field name="taxonomy_names" type="text" indexed="true" stored="false" termVectors="true" multiValued="true" omitNorms="true"/>
290
<!-- The string version of the title is used for sorting -->
291
<copyField source="title" dest="sort_title"/>
292
<!-- The string versions of the name used for sorting/multi-site facets -->
293
<copyField source="name" dest="sname"/>
294
<copyField source="name" dest="sort_name"/>
295
<!-- Copy terms to a single field that contains all taxonomy term names -->
296
<copyField source="ts_vid_*" dest="taxonomy_names"/>
297
<!-- The teaser can be used when a better snippet is not available -->
298
<copyField source="body" dest="teaser" maxChars="300"/>
300
<!-- A set of fields to contain text extracted from tag contents which we
301
can boost at query time. -->
302
<field name="tags_h1" type="text" indexed="true" stored="false" omitNorms="true"/>
303
<field name="tags_h2_h3" type="text" indexed="true" stored="false" omitNorms="true"/>
304
<field name="tags_h4_h5_h6" type="text" indexed="true" stored="false" omitNorms="true"/>
305
<field name="tags_a" type="text" indexed="true" stored="false" omitNorms="true"/>
306
<!-- Inline tags are typically u, b, i, em, strong -->
307
<field name="tags_inline" type="text" indexed="true" stored="false" omitNorms="true"/>
309
<!-- Here, default is used to create a "timestamp" field indicating
310
when each document was indexed.-->
311
<field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
313
<!-- This field is used to build the spellchecker index -->
314
<field name="spell" type="textSpell" indexed="true" stored="true" multiValued="true"/>
316
<!-- copyField commands copy one field to another at the time a document
317
is added to the index. It's used either to index the same field differently,
318
or to add multiple fields to the same field for easier/faster searching. -->
319
<copyField source="title" dest="spell"/>
320
<copyField source="body" dest="spell"/>
322
<!-- Dynamic field definitions. If a field name is not found, dynamicFields
323
will be used if the name matches any of the patterns.
324
RESTRICTION: the glob-like pattern in the name attribute must have
325
a "*" only at the start or the end.
326
EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
327
Longer patterns will be matched first. if equal size patterns
328
both match, the first appearing in the schema will be used. -->
330
<dynamicField name="is_*" type="integer" indexed="true" stored="true" multiValued="false"/>
331
<dynamicField name="im_*" type="integer" indexed="true" stored="true" multiValued="true"/>
332
<dynamicField name="sis_*" type="sint" indexed="true" stored="true" multiValued="false"/>
333
<dynamicField name="sim_*" type="sint" indexed="true" stored="true" multiValued="true"/>
334
<dynamicField name="sm_*" type="string" indexed="true" stored="true" multiValued="true"/>
335
<dynamicField name="tm_*" type="text" indexed="true" stored="true" multiValued="true" termVectors="true"/>
336
<dynamicField name="ss_*" type="string" indexed="true" stored="true" multiValued="false"/>
337
<dynamicField name="ts_*" type="text" indexed="true" stored="true" multiValued="false" termVectors="true"/>
338
<dynamicField name="ds_*" type="date" indexed="true" stored="true" multiValued="false"/>
339
<dynamicField name="dm_*" type="date" indexed="true" stored="true" multiValued="true"/>
340
<dynamicField name="bm_*" type="boolean" indexed="true" stored="true" multiValued="true"/>
341
<dynamicField name="bs_*" type="boolean" indexed="true" stored="true" multiValued="false"/>
342
<dynamicField name="fs_*" type="sfloat" indexed="true" stored="true" multiValued="false"/>
343
<dynamicField name="fm_*" type="sfloat" indexed="true" stored="true" multiValued="true"/>
344
<dynamicField name="ps_*" type="sdouble" indexed="true" stored="true" multiValued="false"/>
345
<dynamicField name="pm_*" type="sdouble" indexed="true" stored="true" multiValued="true"/>
346
<!-- Sortable version of the dynamic string field -->
347
<dynamicField name="sort_ss_*" type="sortString" indexed="true" stored="false"/>
348
<copyField source="ss_*" dest="sort_ss_*"/>
349
<!-- This field is used to store node access records, as opposed to CCK field data -->
350
<dynamicField name="nodeaccess*" type="integer" indexed="true" stored="false" multiValued="true"/>
352
<!-- The following causes solr to ignore any fields that don't already match an existing
353
field name or dynamic field, rather than reporting them as an error.
354
Alternately, change the type="ignored" to some other type e.g. "text" if you want
355
unknown fields indexed and/or stored by default -->
356
<dynamicField name="*" type="ignored" multiValued="true" />
360
<!-- BACKWARDS COMPATIBILITY -->
361
<!-- Here is where we store fields which are no longer used -->
363
<!-- Fields previously used for sorting -->
364
<field name="stitle" type="string" indexed="true" stored="true"/>
365
<field name="title_sort" type="sortString" indexed="true" stored="false"/>
367
<field name="name_sort" type="sortString" indexed="true" stored="false"/>
370
<!-- /BACKWARDS COMPATIBILITY -->
373
<!-- Field to use to determine and enforce document uniqueness.
374
Unless this field is marked with required="false", it will be a required field
376
<uniqueKey>id</uniqueKey>
378
<!-- field for the QueryParser to use when an explicit fieldname is absent -->
379
<defaultSearchField>body</defaultSearchField>
381
<!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
382
<solrQueryParser defaultOperator="AND"/>