forked from subugoe/germania-sacra-daten
-
Notifications
You must be signed in to change notification settings - Fork 0
/
schema.xml
532 lines (462 loc) · 28.4 KB
/
schema.xml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<!--
Schema for Germania Sacra project data.
2013 Sven-S. Porst, SUB Göttingen <porst@sub.uni-goettingen.de>
-->
<schema name="germania-sacra" version="1.5">
<fields>
<!--
Valid attributes for fields:
name: mandatory - the name for the field
type: mandatory - the name of a field type from the
<types> fieldType section
indexed: true if this field should be indexed (searchable or sortable)
stored: true if this field should be retrievable
multiValued: true if this field may contain multiple values per document
omitNorms: (expert) set to true to omit the norms associated with
this field (this disables length normalization and index-time
boosting for the field, and saves some memory). Only full-text
fields or fields that need an index-time boost need norms.
Norms are omitted for primitive (non-analyzed) types by default.
termVectors: [false] set to true to store the term vector for a
given field.
When using MoreLikeThis, fields used for similarity should be
stored for best performance.
termPositions: Store position information with the term vector.
This will increase storage costs.
termOffsets: Store offset information with the term vector. This
will increase storage costs.
required: The field is required. It will throw an error if the
value does not exist
default: a value that should be used if no value is specified
when adding a document.
-->
<!--
field names should consist of alphanumeric or underscore characters only and
not start with a digit. This is not currently strictly enforced,
but other field names will not have first class support from all components
and back compatibility is not guaranteed. Names with both leading and
trailing underscores (e.g. _version_) are reserved.
-->
<field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false"/>
<field name="sql_tabelle" type="string" indexed="true" stored="true"/>
<field name="sql_uid" type="int" indexed="true" stored="true"/>
<field name="typ" type="string" indexed="true" stored="true"/>
<field name="patrozinium" type="text_de" indexed="true" stored="true"/>
<field name="kloster" type="text_de" indexed="true" stored="true"/>
<field name="kloster_id" type="string" indexed="true" stored="true"/>
<field name="bearbeitungsstatus" type="string" indexed="true" stored="true" multiValued="false"/>
<field name="personallistenstatus" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="bemerkung_kloster" type="text_de" indexed="true" stored="true" multiValued="true"/>
<field name="von" type="int" indexed="true" stored="true" multiValued="false"/>
<field name="bis" type="int" indexed="true" stored="true" multiValued="false"/>
<field name="text_gs_band" type="text_de" indexed="true" stored="true" multiValued="true"/>
<field name="band_nummer" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="band_sortierung" type="int" indexed="true" stored="true" multiValued="true"/>
<field name="band_facet" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="band_seite" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="band_titel" type="text_de" indexed="true" stored="true" multiValued="true"/>
<field name="band_kurztitel" type="text_de" indexed="true" stored="true" multiValued="true"/>
<field name="band_id" type="int" indexed="true" stored="true" multiValued="true"/>
<field name="band_url" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="band_url_seitengenau" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="kloster_status" type="text_de" indexed="true" stored="true" multiValued="true"/>
<field name="gruender" type="text_de" indexed="true" stored="true" multiValued="true"/>
<field name="literatur_citekey" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="literatur_beschreibung" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="url" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="url_bemerkung" type="text_de" indexed="true" stored="true" multiValued="true"/>
<field name="url_detail" type="text_de" indexed="true" stored="true" multiValued="true"/>
<field name="url_typ" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="url_relation" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="url_quelle" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="url_quelle_titel" type="text_de" indexed="true" stored="true" multiValued="true"/>
<field name="gnd" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="url_wikipedia" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="geonames" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="koordinaten" type="location_rpt" indexed="true" stored="true" multiValued="true"/>
<field name="koordinaten_institutionengenau" type="boolean" indexed="true" stored="true" multiValued="true"/>
<field name="geohash" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="ort" type="text_de" indexed="true" stored="true" multiValued="true"/>
<field name="ort_uid" type="int" indexed="true" stored="true" multiValued="true"/>
<field name="ort_sort" type="text_general" indexed="true" stored="true" multiValued="false"/>
<field name="gemeinde" type="text_de" indexed="true" stored="true" multiValued="true"/>
<field name="kreis" type="text_de" indexed="true" stored="true" multiValued="true"/>
<field name="land" type="text_de" indexed="true" stored="true" multiValued="true"/>
<field name="ist_in_deutschland" type="boolean" indexed="true" stored="true" multiValued="true"/>
<field name="wuestung" type="boolean" indexed="true" stored="true" multiValued="true"/>
<field name="bemerkung_standort" type="text_de" indexed="true" stored="true" multiValued="true"/>
<field name="bemerkung_kloster_standort" type="text_de" indexed="true" stored="true" multiValued="true"/>
<field name="standort_uid" type="int" indexed="true" stored="true" multiValued="true"/>
<field name="bistum" type="text_de" indexed="true" stored="true" multiValued="true"/>
<field name="bistum_uid" type="int" indexed="true" stored="true" multiValued="true"/>
<field name="bistum_gnd" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="bistum_wikipedia" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="kirchenprovinz" type="text_de" indexed="true" stored="true" multiValued="true"/>
<field name="ist_erzbistum" type="boolean" indexed="true" stored="true" multiValued="true"/>
<field name="orden" type="text_de" indexed="true" stored="true" multiValued="true"/>
<field name="orden_gnd" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="orden_wikipedia" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="orden_graphik" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="orden_ordo" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="orden_symbol" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="orden_typ" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="bemerkung_orden" type="text_de" indexed="true" stored="true" multiValued="true"/>
<field name="kloster_orden_uid" type="int" indexed="true" stored="true" multiValued="true"/>
<field name="orden_standort_von" type="int" indexed="true" stored="true" multiValued="true"/>
<field name="orden_standort_bis" type="int" indexed="true" stored="true" multiValued="true"/>
<field name="orden_standort_jahr50" type="int" indexed="true" stored="false" multiValued="true"/>
<field name="orden_von_von" type="int" indexed="true" stored="true" multiValued="true"/>
<field name="orden_von_bis" type="int" indexed="true" stored="true" multiValued="true"/>
<field name="orden_von_verbal" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="orden_bis_von" type="int" indexed="true" stored="true" multiValued="true"/>
<field name="orden_bis_bis" type="int" indexed="true" stored="true" multiValued="true"/>
<field name="orden_bis_verbal" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="orden_jahr50" type="int" indexed="true" stored="false" multiValued="true"/>
<field name="standort_von_von" type="int" indexed="true" stored="true" multiValued="true"/>
<field name="standort_von_bis" type="int" indexed="true" stored="true" multiValued="true"/>
<field name="standort_von_verbal" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="standort_bis_von" type="int" indexed="true" stored="true" multiValued="true"/>
<field name="standort_bis_bis" type="int" indexed="true" stored="true" multiValued="true"/>
<field name="standort_bis_verbal" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="standort_jahr50" type="int" indexed="true" stored="false" multiValued="true"/>
<field name="jahr50" type="int" indexed="true" stored="false" multiValued="true"/>
<field name="zeitraum_von_von" type="int" indexed="true" stored="false" multiValued="true"/>
<field name="zeitraum_von_bis" type="int" indexed="true" stored="false" multiValued="true"/>
<field name="zeitraum_von_verbal" type="string" indexed="true" stored="false" multiValued="true"/>
<field name="zeitraum_bis_von" type="int" indexed="true" stored="false" multiValued="true"/>
<field name="zeitraum_bis_bis" type="int" indexed="true" stored="false" multiValued="true"/>
<field name="zeitraum_bis_verbal" type="string" indexed="true" stored="false" multiValued="true"/>
<field name="zeitraum_jahr50" type="int" indexed="true" stored="false" multiValued="true"/>
<field name="zeitraum_uid" type="int" indexed="true" stored="true" multiValued="true"/>
<field name="person_name" type="text_de" indexed="true" stored="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
<field name="person_vorname" type="text_de" indexed="true" stored="false" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
<field name="person_namensalternativen" type="text_de" indexed="true" stored="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
<field name="person_anmerkung" type="text_de" indexed="true" stored="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
<field name="person_bezeichnung" type="text_de" indexed="true" stored="true" multiValued="true"/>
<field name="person_bezeichnung_plural" type="text_de" indexed="true" stored="true" multiValued="true"/>
<field name="person_von_verbal" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="person_bis_verbal" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="person_von" type="int" indexed="true" stored="true" multiValued="true"/>
<field name="person_bis" type="int" indexed="true" stored="true" multiValued="true"/>
<field name="person_verbal" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="person_gnd" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="person_gso" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="person_office_id" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="bemerkung" type="text_de" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_facet" type="string" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_suggest" type="phrase_suggest" indexed="true" stored="true" multiValued="true"/>
<field name="text" type="text_de" indexed="true" stored="false" multiValued="true"/>
<field name="_version_" type="long" indexed="true" stored="true"/>
<!--
uncomment the following to ignore any fields that don't already match an existing
field name or dynamic field, rather than reporting them as an error.
alternately, change the type="ignored" to some other type e.g. "text" if you want
unknown fields indexed and/or stored by default
-->
<!--<dynamicField name="*" type="ignored" multiValued="true"/>-->
</fields>
<!--
Field used to determine and enforce document uniqueness.
Unless this field is marked with required="false", it will be a required field
-->
<uniqueKey>id</uniqueKey>
<!--
Copy fields.
-->
<copyField source="kloster_id" dest="text"/>
<copyField source="url" dest="text"/>
<copyField source="patrozinium" dest="text"/>
<copyField source="kloster" dest="text"/>
<copyField source="text_gs_band" dest="text"/>
<copyField source="band_nummer" dest="text"/>
<copyField source="band_titel" dest="text"/>
<copyField source="gruender" dest="text"/>
<copyField source="gnd" dest="text"/>
<!-- <copyField source="geonames" dest="text"/> -->
<copyField source="koordinaten" dest="text"/>
<copyField source="ort" dest="text"/>
<copyField source="gemeinde" dest="text"/>
<copyField source="kreis" dest="text"/>
<copyField source="land" dest="text"/>
<copyField source="bistum" dest="text"/>
<!-- <copyField source="kirchenprovinz" dest="text"/> -->
<copyField source="orden" dest="text"/>
<!-- <copyField source="orden_ordo" dest="text"/> -->
<copyField source="orden_typ" dest="text"/>
<copyField source="person_name" dest="text"/>
<copyField source="person_namensalternativen" dest="text"/>
<copyField source="person_bezeichnung" dest="text"/>
<copyField source="person_gso" dest="text"/>
<copyField source="bemerkung_kloster" dest="bemerkung"/>
<copyField source="bemerkung_standort" dest="bemerkung"/>
<copyField source="bemerkung_kloster_standort" dest="bemerkung"/>
<copyField source="bemerkung_orden" dest="bemerkung"/>
<copyField source="bemerkung_kloster" dest="text"/>
<copyField source="bemerkung_standort" dest="text"/>
<copyField source="bemerkung_kloster_standort" dest="text"/>
<copyField source="bemerkung_orden" dest="text"/>
<copyField source="orden_von_von" dest="zeitraum_von_von"/>
<copyField source="orden_von_bis" dest="zeitraum_von_bis"/>
<copyField source="orden_von_verbal" dest="zeitraum_von_verbal"/>
<copyField source="orden_bis_von" dest="zeitraum_bis_von"/>
<copyField source="orden_bis_bis" dest="zeitraum_bis_von"/>
<copyField source="orden_bis_verbal" dest="zeitraum_bis_verbal"/>
<copyField source="standort_von_von" dest="zeitraum_von_von"/>
<copyField source="standort_von_bis" dest="zeitraum_von_bis"/>
<copyField source="standort_von_verbal" dest="zeitraum_von_verbal"/>
<copyField source="standort_bis_von" dest="zeitraum_bis_von"/>
<copyField source="standort_bis_bis" dest="zeitraum_bis_von"/>
<copyField source="standort_bis_verbal" dest="zeitraum_bis_verbal"/>
<copyField source="orden_von_verbal" dest="text"/>
<copyField source="orden_bis_verbal" dest="text"/>
<copyField source="standort_von_verbal" dest="text"/>
<copyField source="standort_bis_verbal" dest="text"/>
<!-- <copyField source="orden" dest="orden_facet"/> Ordensfacette wird (leicht anders) im Indexierungsskript gefüllt -->
<copyField source="bistum" dest="bistum_facet"/>
<copyField source="land" dest="land_facet"/>
<copyField source="kloster_status" dest="status_facet"/>
<copyField source="kloster" dest="all_suggest"/>
<copyField source="ort" dest="all_suggest"/>
<copyField source="gemeinde" dest="all_suggest"/>
<copyField source="kreis" dest="all_suggest"/>
<copyField source="bistum" dest="all_suggest"/>
<copyField source="orden" dest="all_suggest"/>
<copyField source="kloster" dest="klostername_suggest"/>
<copyField source="bistum" dest="bistum_suggest"/>
<copyField source="orden" dest="orden_suggest"/>
<copyField source="ort" dest="ort_suggest"/>
<types>
<!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
<fieldType name="string" class="solr.StrField" sortMissingLast="true"/>
<!-- boolean type: "true" or "false" -->
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
<!-- Default numeric field types. -->
<fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
<fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
<fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
<fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
<!--
The format for this date field is of the form 1995-12-31T23:59:59Z, and
is a more restricted form of the canonical representation of dateTime
http://www.w3.org/TR/xmlschema-2/#dateTime
The trailing "Z" designates UTC time and is mandatory.
Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
All other components are mandatory.
Expressions can also be used to denote calculations that should be
performed relative to "NOW" to determine the value, ie...
NOW/HOUR
... Round to the start of the current hour
NOW-1DAY
... Exactly 1 day prior to now
NOW/DAY+6MONTHS+3DAYS
... 6 months and 3 days in the future from the start of
the current day
Consult the DateField javadocs for more information.
Note: For faster range queries, consider the tdate type
-->
<fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
<!-- A Trie based date field for faster date range queries and date faceting. -->
<fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
<!--
solr.TextField allows the specification of custom text analyzers
specified as a tokenizer and a list of token filters. Different
analyzers may be specified for indexing and querying.
The optional positionIncrementGap puts space between multiple fields of
this type on the same document, with the purpose of preventing false phrase
matching across fields.
For more info on customizing your analyzer chain, please see
http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
-->
<!--
One can also specify an existing Analyzer class that has a
default constructor via the class attribute on the analyzer element.
Example:
<fieldType name="text_greek" class="solr.TextField">
<analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
</fieldType>
-->
<!-- A text field that only splits on whitespace for exact matching of words -->
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
</analyzer>
</fieldType>
<!--
A general text field that has reasonable, generic
cross-language defaults: it tokenizes with StandardTokenizer,
removes stop words from case-insensitive "stopwords.txt"
(empty by default), and down cases. At query time only, it
also applies synonyms.
-->
<fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true"/>
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-->
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<!--
From:
http://svn.apache.org/repos/asf/lucene/dev/branches/lucene_solr_4_3/solr/core/src/test-files/solr/collection1/conf/schema-phrasesuggest.xml
-->
<fieldtype name="phrase_suggest" class="solr.TextField">
<analyzer>
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.PatternReplaceFilterFactory"
pattern="([^\p{L}\p{M}\p{N}\p{Cs}]*[\p{L}\p{M}\p{N}\p{Cs}\_]+:)|([^\p{L}\p{M}\p{N}\p{Cs}])+"
replacement=" " replace="all"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.TrimFilterFactory"/>
</analyzer>
</fieldtype>
<!--
A text field with defaults appropriate for English: it
(lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
finally applies Porter's stemming. The query time analyzer
also applies synonyms from synonyms.txt.
-->
<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-->
<!--
Case insensitive stop word removal.
add enablePositionIncrements=true in both the index and query
analyzers to leave a 'gap' for more accurate phrase queries.
-->
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt" enablePositionIncrements="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
<filter class="solr.EnglishMinimalStemFilterFactory"/>
-->
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt" enablePositionIncrements="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
<filter class="solr.EnglishMinimalStemFilterFactory"/>
-->
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
</fieldType>
<!--
A text field with defaults appropriate for English, plus
aggressive word-splitting and autophrase features enabled.
This field is just like text_en, except it adds
WordDelimiterFilter to enable splitting and matching of
words on case-change, alpha numeric boundaries, and
non-alphanumeric chars. This means certain compound word
cases will work, for example query "wi fi" will match
document "WiFi" or "wi-fi".
-->
<fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-->
<!--
Case insensitive stop word removal.
add enablePositionIncrements=true in both the index and query
analyzers to leave a 'gap' for more accurate phrase queries.
-->
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt" enablePositionIncrements="true"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt" enablePositionIncrements="true"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
</fieldType>
<!--
Less flexible matching, but less false matches. Probably not ideal for product names,
but may be good for SKUs. Can insert dashes in the wrong place and still match.
-->
<fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.EnglishMinimalStemFilterFactory"/>
<!--
this filter can remove any duplicate tokens that appear at the same position - sometimes
possible with WordDelimiterFilter in conjuncton with stemming.
-->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<!--
Just like text_general except it reverses the characters of
each token, to enable more efficient leading wildcard queries.
-->
<fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.ReversedWildcardFilterFactory" withOriginal="true" maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<!--
since fields of this type are by default not stored or indexed,
any data added to them will be ignored outright.
-->
<fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField"/>
<!--
An alternative geospatial field type new to Solr 4. It supports multiValued and polygon shapes.
For more information about this and other Spatial fields new to Solr 4, see:
http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
-->
<fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
geo="true" distErrPct="0.025" maxDistErr="0.000009" units="degrees" />
<!-- German -->
<fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" enablePositionIncrements="true"/>
<filter class="solr.GermanNormalizationFilterFactory"/>
<filter class="solr.GermanMinimalStemFilterFactory"/>
<!-- more aggressive: <filter class="solr.GermanLightStemFilterFactory"/> -->
<!-- even more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
</analyzer>
</fieldType>
</types>
<solrQueryParser defaultOperator="AND"/>
</schema>