source: sandbox/expresso-solr/solr/example/solr/conf/schema.xml.old @ 7588

Revision 7588, 55.0 KB checked in by adir, 11 years ago (diff)

Ticket #000 - Adicionando a integracao de buscas com Solr na base a ser isnerida na comunidade

Line 
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="1.5">
49  <!-- attribute "name" is the name of this schema and is only used for display purposes.
50       version="x.y" is Solr's version number for the schema syntax and semantics.  It should
51       not normally be changed by applications.
52       1.0: multiValued attribute did not exist, all fields are multiValued by nature
53       1.1: multiValued attribute introduced, false by default
54       1.2: omitTermFreqAndPositions attribute introduced, true by default except for text fields.
55       1.3: removed optional field compress feature
56       1.4: default auto-phrase (QueryParser feature) to off
57       1.5: omitNorms defaults to true for primitive field types (int, float, boolean, string...)
58     -->
59
60 <fields>
61   <!-- Valid attributes for fields:
62     name: mandatory - the name for the field
63     type: mandatory - the name of a field type from the
64       <types> fieldType section
65     indexed: true if this field should be indexed (searchable or sortable)
66     stored: true if this field should be retrievable
67     multiValued: true if this field may contain multiple values per document
68     omitNorms: (expert) set to true to omit the norms associated with
69       this field (this disables length normalization and index-time
70       boosting for the field, and saves some memory).  Only full-text
71       fields or fields that need an index-time boost need norms.
72       Norms are omitted for primitive (non-analyzed) types by default.
73     termVectors: [false] set to true to store the term vector for a
74       given field.
75       When using MoreLikeThis, fields used for similarity should be
76       stored for best performance.
77     termPositions: Store position information with the term vector. 
78       This will increase storage costs.
79     termOffsets: Store offset information with the term vector. This
80       will increase storage costs.
81     required: The field is required.  It will throw an error if the
82       value does not exist
83     default: a value that should be used if no value is specified
84       when adding a document.
85   -->
86
87   <!-- field names should consist of alphanumeric or underscore characters only and
88      not start with a digit.  This is not currently strictly enforced,
89      but other field names will not have first class support from all components
90      and back compatibility is not guaranteed.  Names with both leading and
91      trailing underscores (e.g. _version_) are reserved.
92   -->
93       
94   <field name="id" type="string" indexed="true" stored="true" required="true" />
95   <field name="sku" type="text_en_splitting_tight" indexed="true" stored="true" omitNorms="true"/>
96   <field name="name" type="text_general" indexed="true" stored="true"/>
97   <field name="manu" type="text_general" indexed="true" stored="true" omitNorms="true"/>
98   <field name="cat" type="string" indexed="true" stored="true" multiValued="true"/>
99   <field name="features" type="text_general" indexed="true" stored="true" multiValued="true"/>
100   <field name="includes" type="text_general" indexed="true" stored="true" termVectors="true" termPositions="true" termOffsets="true" />
101
102   <field name="weight" type="float" indexed="true" stored="true"/>
103   <field name="price"  type="float" indexed="true" stored="true"/>
104   <field name="popularity" type="int" indexed="true" stored="true" />
105   <field name="inStock" type="boolean" indexed="true" stored="true" />
106
107   <field name="store" type="location" indexed="true" stored="true"/>
108
109   <!-- Common metadata fields, named specifically to match up with
110     SolrCell metadata when parsing rich documents such as Word, PDF.
111     Some fields are multiValued only because Tika currently may return
112     multiple values for them.
113   -->
114   <field name="title" type="text_general" indexed="true" stored="true" multiValued="true"/>
115   <field name="subject" type="text_general" indexed="true" stored="true"/>
116   <field name="description" type="text_general" indexed="true" stored="true"/>
117   <field name="comments" type="text_general" indexed="true" stored="true"/>
118   <field name="author" type="text_general" indexed="true" stored="true"/>
119   <field name="keywords" type="text_general" indexed="true" stored="true"/>
120   <field name="category" type="text_general" indexed="true" stored="true"/>
121   <field name="content_type" type="string" indexed="true" stored="true" multiValued="true"/>
122   <field name="last_modified" type="date" indexed="true" stored="true"/>
123   <field name="links" type="string" indexed="true" stored="true" multiValued="true"/>
124
125
126   <!-- catchall field, containing all other searchable text fields (implemented
127        via copyField further on in this schema  -->
128   <field name="text" type="text_general" indexed="true" stored="false" multiValued="true"/>
129
130   <!-- catchall text field that indexes tokens both normally and in reverse for efficient
131        leading wildcard queries. -->
132   <field name="text_rev" type="text_general_rev" indexed="true" stored="false" multiValued="true"/>
133
134   <!-- non-tokenized version of manufacturer to make it easier to sort or group
135        results by manufacturer.  copied from "manu" via copyField -->
136   <field name="manu_exact" type="string" indexed="true" stored="false"/>
137
138   <field name="payloads" type="payloads" indexed="true" stored="true"/>
139
140
141   <field name="_version_" type="long" indexed="true" stored="true"/>
142
143   <!-- Uncommenting the following will create a "timestamp" field using
144        a default value of "NOW" to indicate when each document was indexed.
145     -->
146   <!--
147   <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
148     -->
149
150   <!-- Dynamic field definitions allow using convention over configuration
151       for fields via the specification of patterns to match field names.
152       EXAMPLE:  name="*_i" will match any field ending in _i (like myid_i, z_i)
153       RESTRICTION: the glob-like pattern in the name attribute must have
154       a "*" only at the start or the end.  -->
155   
156   <dynamicField name="*_i"  type="int"    indexed="true"  stored="true"/>
157   <dynamicField name="*_is" type="int"    indexed="true"  stored="true"  multiValued="true"/>
158   <dynamicField name="*_s"  type="string"  indexed="true"  stored="true" />
159   <dynamicField name="*_ss" type="string"  indexed="true"  stored="true" multiValued="true"/>
160   <dynamicField name="*_l"  type="long"   indexed="true"  stored="true"/>
161   <dynamicField name="*_ls" type="long"   indexed="true"  stored="true"  multiValued="true"/>
162   <dynamicField name="*_t"  type="text_general"    indexed="true"  stored="true"/>
163   <dynamicField name="*_txt" type="text_general"   indexed="true"  stored="true" multiValued="true"/>
164   <dynamicField name="*_en"  type="text_en"    indexed="true"  stored="true" multiValued="true"/>
165   <dynamicField name="*_b"  type="boolean" indexed="true" stored="true"/>
166   <dynamicField name="*_bs" type="boolean" indexed="true" stored="true"  multiValued="true"/>
167   <dynamicField name="*_f"  type="float"  indexed="true"  stored="true"/>
168   <dynamicField name="*_fs" type="float"  indexed="true"  stored="true"  multiValued="true"/>
169   <dynamicField name="*_d"  type="double" indexed="true"  stored="true"/>
170   <dynamicField name="*_ds" type="double" indexed="true"  stored="true"  multiValued="true"/>
171
172   <!-- Type used to index the lat and lon components for the "location" FieldType -->
173   <dynamicField name="*_coordinate"  type="tdouble" indexed="true"  stored="false" />
174
175   <dynamicField name="*_dt"  type="date"    indexed="true"  stored="true"/>
176   <dynamicField name="*_dts" type="date"    indexed="true"  stored="true" multiValued="true"/>
177   <dynamicField name="*_p"  type="location" indexed="true" stored="true"/>
178
179   <!-- some trie-coded dynamic fields for faster range queries -->
180   <dynamicField name="*_ti" type="tint"    indexed="true"  stored="true"/>
181   <dynamicField name="*_tl" type="tlong"   indexed="true"  stored="true"/>
182   <dynamicField name="*_tf" type="tfloat"  indexed="true"  stored="true"/>
183   <dynamicField name="*_td" type="tdouble" indexed="true"  stored="true"/>
184   <dynamicField name="*_tdt" type="tdate"  indexed="true"  stored="true"/>
185
186   <dynamicField name="*_pi"  type="pint"    indexed="true"  stored="true"/>
187   <dynamicField name="*_c"   type="currency" indexed="true"  stored="true"/>
188
189   <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
190   <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
191
192   <dynamicField name="random_*" type="random" />
193
194   <!-- uncomment the following to ignore any fields that don't already match an existing
195        field name or dynamic field, rather than reporting them as an error.
196        alternately, change the type="ignored" to some other type e.g. "text" if you want
197        unknown fields indexed and/or stored by default -->
198   <!--dynamicField name="*" type="ignored" multiValued="true" /-->
199   
200 </fields>
201
202
203 <!-- Field to use to determine and enforce document uniqueness.
204      Unless this field is marked with required="false", it will be a required field
205   -->
206 <uniqueKey>id</uniqueKey>
207
208 <!-- DEPRECATED: The defaultSearchField is consulted by various query parsers when
209  parsing a query string that isn't explicit about the field.  Machine (non-user)
210  generated queries are best made explicit, or they can use the "df" request parameter
211  which takes precedence over this.
212  Note: Un-commenting defaultSearchField will be insufficient if your request handler
213  in solrconfig.xml defines "df", which takes precedence. That would need to be removed.
214 <defaultSearchField>text</defaultSearchField> -->
215
216 <!-- DEPRECATED: The defaultOperator (AND|OR) is consulted by various query parsers
217  when parsing a query string to determine if a clause of the query should be marked as
218  required or optional, assuming the clause isn't already marked by some operator.
219  The default is OR, which is generally assumed so it is not a good idea to change it
220  globally here.  The "q.op" request parameter takes precedence over this.
221 <solrQueryParser defaultOperator="OR"/> -->
222
223  <!-- copyField commands copy one field to another at the time a document
224        is added to the index.  It's used either to index the same field differently,
225        or to add multiple fields to the same field for easier/faster searching.  -->
226
227   <copyField source="cat" dest="text"/>
228   <copyField source="name" dest="text"/>
229   <copyField source="manu" dest="text"/>
230   <copyField source="features" dest="text"/>
231   <copyField source="includes" dest="text"/>
232   <copyField source="manu" dest="manu_exact"/>
233
234   <!-- Copy the price into a currency enabled field (default USD) -->
235   <copyField source="price" dest="price_c"/>
236       
237   <!-- Above, multiple source fields are copied to the [text] field.
238          Another way to map multiple source fields to the same
239          destination field is to use the dynamic field syntax.
240          copyField also supports a maxChars to copy setting.  -->
241           
242   <!-- <copyField source="*_t" dest="text" maxChars="3000"/> -->
243
244   <!-- copy name to alphaNameSort, a field designed for sorting by name -->
245   <!-- <copyField source="name" dest="alphaNameSort"/> -->
246 
247
248 <!-- Similarity is the scoring routine for each document vs. a query.
249      A custom similarity may be specified here, but the default is fine
250      for most applications.  -->
251 <!-- <similarity class="org.apache.lucene.search.similarities.DefaultSimilarity"/> -->
252 <!-- ... OR ...
253      Specify a SimilarityFactory class name implementation
254      allowing parameters to be used.
255 -->
256 <!--
257 <similarity class="com.example.solr.CustomSimilarityFactory">
258   <str name="paramkey">param value</str>
259 </similarity>
260 -->
261
262
263
264  <types>
265    <!-- field type definitions. The "name" attribute is
266       just a label to be used by field definitions.  The "class"
267       attribute and any other attributes determine the real
268       behavior of the fieldType.
269         Class names starting with "solr" refer to java classes in a
270       standard package such as org.apache.solr.analysis
271    -->
272
273    <!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
274    <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
275
276    <!-- boolean type: "true" or "false" -->
277    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
278
279    <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
280         currently supported on types that are sorted internally as strings
281         and on numeric types.
282             This includes "string","boolean", and, as of 3.5 (and 4.x),
283             int, float, long, date, double, including the "Trie" variants.
284       - If sortMissingLast="true", then a sort on this field will cause documents
285         without the field to come after documents with the field,
286         regardless of the requested sort order (asc or desc).
287       - If sortMissingFirst="true", then a sort on this field will cause documents
288         without the field to come before documents with the field,
289         regardless of the requested sort order.
290       - If sortMissingLast="false" and sortMissingFirst="false" (the default),
291         then default lucene sorting will be used which places docs without the
292         field first in an ascending sort and last in a descending sort.
293    -->   
294
295    <!--
296      Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
297    -->
298    <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
299    <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
300    <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
301    <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
302
303    <!--
304     Numeric field types that index each value at various levels of precision
305     to accelerate range queries when the number of values between the range
306     endpoints is large. See the javadoc for NumericRangeQuery for internal
307     implementation details.
308
309     Smaller precisionStep values (specified in bits) will lead to more tokens
310     indexed per value, slightly larger index size, and faster range queries.
311     A precisionStep of 0 disables indexing at different precision levels.
312    -->
313    <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
314    <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
315    <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
316    <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
317
318    <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
319         is a more restricted form of the canonical representation of dateTime
320         http://www.w3.org/TR/xmlschema-2/#dateTime   
321         The trailing "Z" designates UTC time and is mandatory.
322         Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
323         All other components are mandatory.
324
325         Expressions can also be used to denote calculations that should be
326         performed relative to "NOW" to determine the value, ie...
327
328               NOW/HOUR
329                  ... Round to the start of the current hour
330               NOW-1DAY
331                  ... Exactly 1 day prior to now
332               NOW/DAY+6MONTHS+3DAYS
333                  ... 6 months and 3 days in the future from the start of
334                      the current day
335                     
336         Consult the DateField javadocs for more information.
337
338         Note: For faster range queries, consider the tdate type
339      -->
340    <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
341
342    <!-- A Trie based date field for faster date range queries and date faceting. -->
343    <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
344
345
346    <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
347    <fieldtype name="binary" class="solr.BinaryField"/>
348
349    <!--
350      Note:
351      These should only be used for compatibility with existing indexes (created with lucene or older Solr versions).
352      Use Trie based fields instead. As of Solr 3.5 and 4.x, Trie based fields support sortMissingFirst/Last
353     
354      Plain numeric field types that store and index the text
355      value verbatim (and hence don't correctly support range queries, since the
356      lexicographic ordering isn't equal to the numeric ordering)
357    -->
358    <fieldType name="pint" class="solr.IntField"/>
359    <fieldType name="plong" class="solr.LongField"/>
360    <fieldType name="pfloat" class="solr.FloatField"/>
361    <fieldType name="pdouble" class="solr.DoubleField"/>
362    <fieldType name="pdate" class="solr.DateField" sortMissingLast="true"/>
363
364    <!-- The "RandomSortField" is not used to store or search any
365         data.  You can declare fields of this type it in your schema
366         to generate pseudo-random orderings of your docs for sorting
367         or function purposes.  The ordering is generated based on the field
368         name and the version of the index. As long as the index version
369         remains unchanged, and the same field name is reused,
370         the ordering of the docs will be consistent. 
371         If you want different psuedo-random orderings of documents,
372         for the same version of the index, use a dynamicField and
373         change the field name in the request.
374     -->
375    <fieldType name="random" class="solr.RandomSortField" indexed="true" />
376
377    <!-- solr.TextField allows the specification of custom text analyzers
378         specified as a tokenizer and a list of token filters. Different
379         analyzers may be specified for indexing and querying.
380
381         The optional positionIncrementGap puts space between multiple fields of
382         this type on the same document, with the purpose of preventing false phrase
383         matching across fields.
384
385         For more info on customizing your analyzer chain, please see
386         http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
387     -->
388
389    <!-- One can also specify an existing Analyzer class that has a
390         default constructor via the class attribute on the analyzer element.
391         Example:
392    <fieldType name="text_greek" class="solr.TextField">
393      <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
394    </fieldType>
395    -->
396
397    <!-- A text field that only splits on whitespace for exact matching of words -->
398    <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
399      <analyzer>
400        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
401      </analyzer>
402    </fieldType>
403
404    <!-- A general text field that has reasonable, generic
405         cross-language defaults: it tokenizes with StandardTokenizer,
406         removes stop words from case-insensitive "stopwords.txt"
407         (empty by default), and down cases.  At query time only, it
408         also applies synonyms. -->
409    <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
410      <analyzer type="index">
411        <tokenizer class="solr.StandardTokenizerFactory"/>
412        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
413        <!-- in this example, we will only use synonyms at query time
414        <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
415        -->
416        <filter class="solr.LowerCaseFilterFactory"/>
417      </analyzer>
418      <analyzer type="query">
419        <tokenizer class="solr.StandardTokenizerFactory"/>
420        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
421        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
422        <filter class="solr.LowerCaseFilterFactory"/>
423      </analyzer>
424    </fieldType>
425
426    <!-- A text field with defaults appropriate for English: it
427         tokenizes with StandardTokenizer, removes English stop words
428         (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
429         finally applies Porter's stemming.  The query time analyzer
430         also applies synonyms from synonyms.txt. -->
431    <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
432      <analyzer type="index">
433        <tokenizer class="solr.StandardTokenizerFactory"/>
434        <!-- in this example, we will only use synonyms at query time
435        <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
436        -->
437        <!-- Case insensitive stop word removal.
438          add enablePositionIncrements=true in both the index and query
439          analyzers to leave a 'gap' for more accurate phrase queries.
440        -->
441        <filter class="solr.StopFilterFactory"
442                ignoreCase="true"
443                words="lang/stopwords_en.txt"
444                enablePositionIncrements="true"
445                />
446        <filter class="solr.LowerCaseFilterFactory"/>
447        <filter class="solr.EnglishPossessiveFilterFactory"/>
448        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
449        <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
450        <filter class="solr.EnglishMinimalStemFilterFactory"/>
451        -->
452        <filter class="solr.PorterStemFilterFactory"/>
453      </analyzer>
454      <analyzer type="query">
455        <tokenizer class="solr.StandardTokenizerFactory"/>
456        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
457        <filter class="solr.StopFilterFactory"
458                ignoreCase="true"
459                words="lang/stopwords_en.txt"
460                enablePositionIncrements="true"
461                />
462        <filter class="solr.LowerCaseFilterFactory"/>
463        <filter class="solr.EnglishPossessiveFilterFactory"/>
464        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
465        <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
466        <filter class="solr.EnglishMinimalStemFilterFactory"/>
467        -->
468        <filter class="solr.PorterStemFilterFactory"/>
469      </analyzer>
470    </fieldType>
471
472    <!-- A text field with defaults appropriate for English, plus
473         aggressive word-splitting and autophrase features enabled.
474         This field is just like text_en, except it adds
475         WordDelimiterFilter to enable splitting and matching of
476         words on case-change, alpha numeric boundaries, and
477         non-alphanumeric chars.  This means certain compound word
478         cases will work, for example query "wi fi" will match
479         document "WiFi" or "wi-fi".
480        -->
481    <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
482      <analyzer type="index">
483        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
484        <!-- in this example, we will only use synonyms at query time
485        <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
486        -->
487        <!-- Case insensitive stop word removal.
488          add enablePositionIncrements=true in both the index and query
489          analyzers to leave a 'gap' for more accurate phrase queries.
490        -->
491        <filter class="solr.StopFilterFactory"
492                ignoreCase="true"
493                words="lang/stopwords_en.txt"
494                enablePositionIncrements="true"
495                />
496        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
497        <filter class="solr.LowerCaseFilterFactory"/>
498        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
499        <filter class="solr.PorterStemFilterFactory"/>
500      </analyzer>
501      <analyzer type="query">
502        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
503        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
504        <filter class="solr.StopFilterFactory"
505                ignoreCase="true"
506                words="lang/stopwords_en.txt"
507                enablePositionIncrements="true"
508                />
509        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
510        <filter class="solr.LowerCaseFilterFactory"/>
511        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
512        <filter class="solr.PorterStemFilterFactory"/>
513      </analyzer>
514    </fieldType>
515
516    <!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
517         but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
518    <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
519      <analyzer>
520        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
521        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
522        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
523        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
524        <filter class="solr.LowerCaseFilterFactory"/>
525        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
526        <filter class="solr.EnglishMinimalStemFilterFactory"/>
527        <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
528             possible with WordDelimiterFilter in conjuncton with stemming. -->
529        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
530      </analyzer>
531    </fieldType>
532
533    <!-- Just like text_general except it reverses the characters of
534         each token, to enable more efficient leading wildcard queries. -->
535    <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
536      <analyzer type="index">
537        <tokenizer class="solr.StandardTokenizerFactory"/>
538        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
539        <filter class="solr.LowerCaseFilterFactory"/>
540        <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
541           maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
542      </analyzer>
543      <analyzer type="query">
544        <tokenizer class="solr.StandardTokenizerFactory"/>
545        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
546        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
547        <filter class="solr.LowerCaseFilterFactory"/>
548      </analyzer>
549    </fieldType>
550
551    <!-- charFilter + WhitespaceTokenizer  -->
552    <!--
553    <fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
554      <analyzer>
555        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
556        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
557      </analyzer>
558    </fieldType>
559    -->
560
561    <!-- This is an example of using the KeywordTokenizer along
562         With various TokenFilterFactories to produce a sortable field
563         that does not include some properties of the source text
564      -->
565    <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
566      <analyzer>
567        <!-- KeywordTokenizer does no actual tokenizing, so the entire
568             input string is preserved as a single token
569          -->
570        <tokenizer class="solr.KeywordTokenizerFactory"/>
571        <!-- The LowerCase TokenFilter does what you expect, which can be
572             when you want your sorting to be case insensitive
573          -->
574        <filter class="solr.LowerCaseFilterFactory" />
575        <!-- The TrimFilter removes any leading or trailing whitespace -->
576        <filter class="solr.TrimFilterFactory" />
577        <!-- The PatternReplaceFilter gives you the flexibility to use
578             Java Regular expression to replace any sequence of characters
579             matching a pattern with an arbitrary replacement string,
580             which may include back references to portions of the original
581             string matched by the pattern.
582             
583             See the Java Regular Expression documentation for more
584             information on pattern and replacement string syntax.
585             
586             http://java.sun.com/j2se/1.6.0/docs/api/java/util/regex/package-summary.html
587          -->
588        <filter class="solr.PatternReplaceFilterFactory"
589                pattern="([^a-z])" replacement="" replace="all"
590        />
591      </analyzer>
592    </fieldType>
593   
594    <fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
595      <analyzer>
596        <tokenizer class="solr.StandardTokenizerFactory"/>
597        <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
598      </analyzer>
599    </fieldtype>
600
601    <fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
602      <analyzer>
603        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
604        <!--
605        The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
606        a token of "foo|1.4"  would be indexed as "foo" with a payload of 1.4f
607        Attributes of the DelimitedPayloadTokenFilterFactory :
608         "delimiter" - a one character delimiter. Default is | (pipe)
609         "encoder" - how to encode the following value into a playload
610            float -> org.apache.lucene.analysis.payloads.FloatEncoder,
611            integer -> o.a.l.a.p.IntegerEncoder
612            identity -> o.a.l.a.p.IdentityEncoder
613            Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
614         -->
615        <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
616      </analyzer>
617    </fieldtype>
618
619    <!-- lowercases the entire field value, keeping it as a single token.  -->
620    <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
621      <analyzer>
622        <tokenizer class="solr.KeywordTokenizerFactory"/>
623        <filter class="solr.LowerCaseFilterFactory" />
624      </analyzer>
625    </fieldType>
626
627    <fieldType name="text_path" class="solr.TextField" positionIncrementGap="100">
628      <analyzer>
629        <tokenizer class="solr.PathHierarchyTokenizerFactory"/>
630      </analyzer>
631    </fieldType>
632
633
634    <!-- since fields of this type are by default not stored or indexed,
635         any data added to them will be ignored outright.  -->
636    <fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
637
638    <!-- This point type indexes the coordinates as separate fields (subFields)
639      If subFieldType is defined, it references a type, and a dynamic field
640      definition is created matching *___<typename>.  Alternately, if
641      subFieldSuffix is defined, that is used to create the subFields.
642      Example: if subFieldType="double", then the coordinates would be
643        indexed in fields myloc_0___double,myloc_1___double.
644      Example: if subFieldSuffix="_d" then the coordinates would be indexed
645        in fields myloc_0_d,myloc_1_d
646      The subFields are an implementation detail of the fieldType, and end
647      users normally should not need to know about them.
648     -->
649    <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
650
651    <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
652    <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
653
654   <!--
655    A Geohash is a compact representation of a latitude longitude pair in a single field.
656    See http://wiki.apache.org/solr/SpatialSearch
657   -->
658    <fieldtype name="geohash" class="solr.GeoHashField"/>
659
660   <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
661        Parameters:
662          defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
663          precisionStep:   Specifies the precisionStep for the TrieLong field used for the amount
664          providerClass:   Lets you plug in other exchange provider backend:
665                           solr.FileExchangeRateProvider is the default and takes one parameter:
666                             currencyConfig: name of an xml file holding exhange rates
667                           solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
668                             ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
669                             refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
670   -->
671    <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
672             
673
674
675   <!-- some examples for different languages (generally ordered by ISO code) -->
676
677    <!-- Arabic -->
678    <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
679      <analyzer>
680        <tokenizer class="solr.StandardTokenizerFactory"/>
681        <!-- for any non-arabic -->
682        <filter class="solr.LowerCaseFilterFactory"/>
683        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" enablePositionIncrements="true"/>
684        <!-- normalizes ﻯ to ï»±, etc -->
685        <filter class="solr.ArabicNormalizationFilterFactory"/>
686        <filter class="solr.ArabicStemFilterFactory"/>
687      </analyzer>
688    </fieldType>
689
690    <!-- Bulgarian -->
691    <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
692      <analyzer>
693        <tokenizer class="solr.StandardTokenizerFactory"/>
694        <filter class="solr.LowerCaseFilterFactory"/>
695        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" enablePositionIncrements="true"/>
696        <filter class="solr.BulgarianStemFilterFactory"/>       
697      </analyzer>
698    </fieldType>
699   
700    <!-- Catalan -->
701    <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
702      <analyzer>
703        <tokenizer class="solr.StandardTokenizerFactory"/>
704        <!-- removes l', etc -->
705        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
706        <filter class="solr.LowerCaseFilterFactory"/>
707        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" enablePositionIncrements="true"/>
708        <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>       
709      </analyzer>
710    </fieldType>
711   
712    <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
713    <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
714      <analyzer>
715        <tokenizer class="solr.StandardTokenizerFactory"/>
716        <!-- normalize width before bigram, as e.g. half-width dakuten combine  -->
717        <filter class="solr.CJKWidthFilterFactory"/>
718        <!-- for any non-CJK -->
719        <filter class="solr.LowerCaseFilterFactory"/>
720        <filter class="solr.CJKBigramFilterFactory"/>
721      </analyzer>
722    </fieldType>
723
724    <!-- Czech -->
725    <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
726      <analyzer>
727        <tokenizer class="solr.StandardTokenizerFactory"/>
728        <filter class="solr.LowerCaseFilterFactory"/>
729        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" enablePositionIncrements="true"/>
730        <filter class="solr.CzechStemFilterFactory"/>       
731      </analyzer>
732    </fieldType>
733   
734    <!-- Danish -->
735    <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
736      <analyzer>
737        <tokenizer class="solr.StandardTokenizerFactory"/>
738        <filter class="solr.LowerCaseFilterFactory"/>
739        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" enablePositionIncrements="true"/>
740        <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>       
741      </analyzer>
742    </fieldType>
743   
744    <!-- German -->
745    <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
746      <analyzer>
747        <tokenizer class="solr.StandardTokenizerFactory"/>
748        <filter class="solr.LowerCaseFilterFactory"/>
749        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" enablePositionIncrements="true"/>
750        <filter class="solr.GermanNormalizationFilterFactory"/>
751        <filter class="solr.GermanLightStemFilterFactory"/>
752        <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
753        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
754      </analyzer>
755    </fieldType>
756   
757    <!-- Greek -->
758    <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
759      <analyzer>
760        <tokenizer class="solr.StandardTokenizerFactory"/>
761        <!-- greek specific lowercase for sigma -->
762        <filter class="solr.GreekLowerCaseFilterFactory"/>
763        <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" enablePositionIncrements="true"/>
764        <filter class="solr.GreekStemFilterFactory"/>
765      </analyzer>
766    </fieldType>
767   
768    <!-- Spanish -->
769    <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
770      <analyzer>
771        <tokenizer class="solr.StandardTokenizerFactory"/>
772        <filter class="solr.LowerCaseFilterFactory"/>
773        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" enablePositionIncrements="true"/>
774        <filter class="solr.SpanishLightStemFilterFactory"/>
775        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
776      </analyzer>
777    </fieldType>
778   
779    <!-- Basque -->
780    <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
781      <analyzer>
782        <tokenizer class="solr.StandardTokenizerFactory"/>
783        <filter class="solr.LowerCaseFilterFactory"/>
784        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" enablePositionIncrements="true"/>
785        <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
786      </analyzer>
787    </fieldType>
788   
789    <!-- Persian -->
790    <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
791      <analyzer>
792        <!-- for ZWNJ -->
793        <charFilter class="solr.PersianCharFilterFactory"/>
794        <tokenizer class="solr.StandardTokenizerFactory"/>
795        <filter class="solr.LowerCaseFilterFactory"/>
796        <filter class="solr.ArabicNormalizationFilterFactory"/>
797        <filter class="solr.PersianNormalizationFilterFactory"/>
798        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" enablePositionIncrements="true"/>
799      </analyzer>
800    </fieldType>
801   
802    <!-- Finnish -->
803    <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
804      <analyzer>
805        <tokenizer class="solr.StandardTokenizerFactory"/>
806        <filter class="solr.LowerCaseFilterFactory"/>
807        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" enablePositionIncrements="true"/>
808        <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
809        <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
810      </analyzer>
811    </fieldType>
812   
813    <!-- French -->
814    <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
815      <analyzer>
816        <tokenizer class="solr.StandardTokenizerFactory"/>
817        <!-- removes l', etc -->
818        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
819        <filter class="solr.LowerCaseFilterFactory"/>
820        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" enablePositionIncrements="true"/>
821        <filter class="solr.FrenchLightStemFilterFactory"/>
822        <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
823        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
824      </analyzer>
825    </fieldType>
826   
827    <!-- Irish -->
828    <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
829      <analyzer>
830        <tokenizer class="solr.StandardTokenizerFactory"/>
831        <!-- removes d', etc -->
832        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
833        <!-- removes n-, etc. position increments is intentionally false! -->
834        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt" enablePositionIncrements="false"/>
835        <filter class="solr.IrishLowerCaseFilterFactory"/>
836        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt" enablePositionIncrements="true"/>
837        <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
838      </analyzer>
839    </fieldType>
840   
841    <!-- Galician -->
842    <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
843      <analyzer>
844        <tokenizer class="solr.StandardTokenizerFactory"/>
845        <filter class="solr.LowerCaseFilterFactory"/>
846        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" enablePositionIncrements="true"/>
847        <filter class="solr.GalicianStemFilterFactory"/>
848        <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
849      </analyzer>
850    </fieldType>
851   
852    <!-- Hindi -->
853    <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
854      <analyzer>
855        <tokenizer class="solr.StandardTokenizerFactory"/>
856        <filter class="solr.LowerCaseFilterFactory"/>
857        <!-- normalizes unicode representation -->
858        <filter class="solr.IndicNormalizationFilterFactory"/>
859        <!-- normalizes variation in spelling -->
860        <filter class="solr.HindiNormalizationFilterFactory"/>
861        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" enablePositionIncrements="true"/>
862        <filter class="solr.HindiStemFilterFactory"/>
863      </analyzer>
864    </fieldType>
865   
866    <!-- Hungarian -->
867    <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
868      <analyzer>
869        <tokenizer class="solr.StandardTokenizerFactory"/>
870        <filter class="solr.LowerCaseFilterFactory"/>
871        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" enablePositionIncrements="true"/>
872        <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
873        <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->   
874      </analyzer>
875    </fieldType>
876   
877    <!-- Armenian -->
878    <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
879      <analyzer>
880        <tokenizer class="solr.StandardTokenizerFactory"/>
881        <filter class="solr.LowerCaseFilterFactory"/>
882        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" enablePositionIncrements="true"/>
883        <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
884      </analyzer>
885    </fieldType>
886   
887    <!-- Indonesian -->
888    <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
889      <analyzer>
890        <tokenizer class="solr.StandardTokenizerFactory"/>
891        <filter class="solr.LowerCaseFilterFactory"/>
892        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" enablePositionIncrements="true"/>
893        <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
894        <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
895      </analyzer>
896    </fieldType>
897   
898    <!-- Italian -->
899    <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
900      <analyzer>
901        <tokenizer class="solr.StandardTokenizerFactory"/>
902        <!-- removes l', etc -->
903        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
904        <filter class="solr.LowerCaseFilterFactory"/>
905        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" enablePositionIncrements="true"/>
906        <filter class="solr.ItalianLightStemFilterFactory"/>
907        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
908      </analyzer>
909    </fieldType>
910   
911    <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
912
913         NOTE: If you want to optimize search for precision, use default operator AND in your query
914         parser config with <solrQueryParser defaultOperator="AND"/> further down in this file.  Use
915         OR if you would like to optimize for recall (default).
916    -->
917    <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
918      <analyzer>
919      <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
920
921           Kuromoji has a search mode (default) that does segmentation useful for search.  A heuristic
922           is used to segment compounds into its parts and the compound itself is kept as synonym.
923
924           Valid values for attribute mode are:
925              normal: regular segmentation
926              search: segmentation useful for search with synonyms compounds (default)
927            extended: same as search mode, but unigrams unknown words (experimental)
928
929           For some applications it might be good to use search mode for indexing and normal mode for
930           queries to reduce recall and prevent parts of compounds from being matched and highlighted.
931           Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
932
933           Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
934           model with your own entries for segmentation, part-of-speech tags and readings without a need
935           to specify weights.  Notice that user dictionaries have not been subject to extensive testing.
936
937           User dictionary attributes are:
938                     userDictionary: user dictionary filename
939             userDictionaryEncoding: user dictionary encoding (default is UTF-8)
940
941           See lang/userdict_ja.txt for a sample user dictionary file.
942
943           See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
944        -->
945        <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
946        <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
947        <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (蟞曞圢) -->
948        <filter class="solr.JapaneseBaseFormFilterFactory"/>
949        <!-- Removes tokens with certain part-of-speech tags -->
950        <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" enablePositionIncrements="true"/>
951        <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
952        <filter class="solr.CJKWidthFilterFactory"/>
953        <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
954        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" enablePositionIncrements="true" />
955        <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
956        <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
957        <!-- Lower-cases romaji characters -->
958        <filter class="solr.LowerCaseFilterFactory"/>
959      </analyzer>
960    </fieldType>
961   
962    <!-- Latvian -->
963    <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
964      <analyzer>
965        <tokenizer class="solr.StandardTokenizerFactory"/>
966        <filter class="solr.LowerCaseFilterFactory"/>
967        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" enablePositionIncrements="true"/>
968        <filter class="solr.LatvianStemFilterFactory"/>
969      </analyzer>
970    </fieldType>
971   
972    <!-- Dutch -->
973    <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
974      <analyzer>
975        <tokenizer class="solr.StandardTokenizerFactory"/>
976        <filter class="solr.LowerCaseFilterFactory"/>
977        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" enablePositionIncrements="true"/>
978        <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
979        <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
980      </analyzer>
981    </fieldType>
982   
983    <!-- Norwegian -->
984    <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
985      <analyzer>
986        <tokenizer class="solr.StandardTokenizerFactory"/>
987        <filter class="solr.LowerCaseFilterFactory"/>
988        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" enablePositionIncrements="true"/>
989        <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
990        <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> -->
991        <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
992      </analyzer>
993    </fieldType>
994   
995    <!-- Portuguese -->
996    <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
997      <analyzer>
998        <tokenizer class="solr.StandardTokenizerFactory"/>
999        <filter class="solr.LowerCaseFilterFactory"/>
1000        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" enablePositionIncrements="true"/>
1001        <filter class="solr.PortugueseLightStemFilterFactory"/>
1002        <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
1003        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
1004        <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
1005      </analyzer>
1006    </fieldType>
1007   
1008    <!-- Romanian -->
1009    <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
1010      <analyzer>
1011        <tokenizer class="solr.StandardTokenizerFactory"/>
1012        <filter class="solr.LowerCaseFilterFactory"/>
1013        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" enablePositionIncrements="true"/>
1014        <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
1015      </analyzer>
1016    </fieldType>
1017   
1018    <!-- Russian -->
1019    <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
1020      <analyzer>
1021        <tokenizer class="solr.StandardTokenizerFactory"/>
1022        <filter class="solr.LowerCaseFilterFactory"/>
1023        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" enablePositionIncrements="true"/>
1024        <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
1025        <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
1026      </analyzer>
1027    </fieldType>
1028   
1029    <!-- Swedish -->
1030    <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
1031      <analyzer>
1032        <tokenizer class="solr.StandardTokenizerFactory"/>
1033        <filter class="solr.LowerCaseFilterFactory"/>
1034        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" enablePositionIncrements="true"/>
1035        <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
1036        <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
1037      </analyzer>
1038    </fieldType>
1039   
1040    <!-- Thai -->
1041    <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
1042      <analyzer>
1043        <tokenizer class="solr.StandardTokenizerFactory"/>
1044        <filter class="solr.LowerCaseFilterFactory"/>
1045        <filter class="solr.ThaiWordFilterFactory"/>
1046        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" enablePositionIncrements="true"/>
1047      </analyzer>
1048    </fieldType>
1049   
1050    <!-- Turkish -->
1051    <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
1052      <analyzer>
1053        <tokenizer class="solr.StandardTokenizerFactory"/>
1054        <filter class="solr.TurkishLowerCaseFilterFactory"/>
1055        <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" enablePositionIncrements="true"/>
1056        <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
1057      </analyzer>
1058    </fieldType>
1059 </types>
1060
1061
1062
1063</schema>
Note: See TracBrowser for help on using the repository browser.