source: solr/trunk/example/solr/conf/schema.xml @ 0:2f43cb89e87c

Revision 0:2f43cb89e87c, 30.3 KB checked in by andre.hagenbruch@rub.de, 8 years ago (diff)

Initial commit for version 0.2

  • Property exe set to *
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 NOTE: this schema includes many optional features and should not
32 be used for benchmarking.
33-->
34
35<schema name="example" version="1.2">
36  <!-- attribute "name" is the name of this schema and is only used for display purposes.
37       Applications should change this to reflect the nature of the search collection.
38       version="1.2" is Solr's version number for the schema syntax and semantics.  It should
39       not normally be changed by applications.
40       1.0: multiValued attribute did not exist, all fields are multiValued by nature
41       1.1: multiValued attribute introduced, false by default
42       1.2: omitTermFreqAndPositions attribute introduced, true by default except for text fields.
43     -->
44
45  <types>
46    <!-- field type definitions. The "name" attribute is
47       just a label to be used by field definitions.  The "class"
48       attribute and any other attributes determine the real
49       behavior of the fieldType.
50         Class names starting with "solr" refer to java classes in the
51       org.apache.solr.analysis package.
52    -->
53
54    <!-- The StrField type is not analyzed, but indexed/stored verbatim. 
55       - StrField and TextField support an optional compressThreshold which
56       limits compression (if enabled in the derived fields) to values which
57       exceed a certain size (in characters).
58    -->
59    <fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
60
61    <!-- boolean type: "true" or "false" -->
62    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
63
64    <!-- The optional sortMissingLast and sortMissingFirst attributes are
65         currently supported on types that are sorted internally as strings.
66       - If sortMissingLast="true", then a sort on this field will cause documents
67         without the field to come after documents with the field,
68         regardless of the requested sort order (asc or desc).
69       - If sortMissingFirst="true", then a sort on this field will cause documents
70         without the field to come before documents with the field,
71         regardless of the requested sort order.
72       - If sortMissingLast="false" and sortMissingFirst="false" (the default),
73         then default lucene sorting will be used which places docs without the
74         field first in an ascending sort and last in a descending sort.
75    -->   
76
77
78    <!-- numeric field types that store and index the text
79         value verbatim (and hence don't support range queries, since the
80         lexicographic ordering isn't equal to the numeric ordering) -->
81    <fieldType name="integer" class="solr.IntField" omitNorms="true"/>
82    <fieldType name="long" class="solr.LongField" omitNorms="true"/>
83    <fieldType name="float" class="solr.FloatField" omitNorms="true"/>
84    <fieldType name="double" class="solr.DoubleField" omitNorms="true"/>
85
86
87    <!-- Numeric field types that manipulate the value into
88         a string value that isn't human-readable in its internal form,
89         but with a lexicographic ordering the same as the numeric ordering,
90         so that range queries work correctly. -->
91    <fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/>
92    <fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/>
93    <fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/>
94    <fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/>
95
96
97    <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
98         is a more restricted form of the canonical representation of dateTime
99         http://www.w3.org/TR/xmlschema-2/#dateTime   
100         The trailing "Z" designates UTC time and is mandatory.
101         Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
102         All other components are mandatory.
103
104         Expressions can also be used to denote calculations that should be
105         performed relative to "NOW" to determine the value, ie...
106
107               NOW/HOUR
108                  ... Round to the start of the current hour
109               NOW-1DAY
110                  ... Exactly 1 day prior to now
111               NOW/DAY+6MONTHS+3DAYS
112                  ... 6 months and 3 days in the future from the start of
113                      the current day
114                     
115         Consult the DateField javadocs for more information.
116      -->
117    <fieldType name="date" class="solr.DateField" sortMissingLast="true" omitNorms="true"/>
118
119    <!--
120          Numeric field types that manipulate the value into trie encoded strings which are not
121          human readable in the internal form. Range searches on such fields use the fast Trie Range Queries
122          which are much faster than range searches on the SortableNumberField types.
123
124          For the fast range search to work, trie fields must be indexed.
125
126          For each number being added to this field, multiple terms are generated as per the algorithm described in
127          org.apache.lucene.search.trie package description. The possible number of terms depend on the precisionStep
128          attribute and increase dramatically with higher precision steps (factor 2**precisionStep). The default
129          value of precisionStep is 8.
130         
131          Note that if you use a precisionStep of 32 for int/float and 64 for long/double, then multiple terms
132          will not be generated, and range search will be no faster than any other number field.
133     -->
134    <fieldType name="tint" class="solr.TrieField" type="integer" omitNorms="true" positionIncrementGap="0" indexed="true" stored="false" />
135    <fieldType name="tfloat" class="solr.TrieField" type="float" omitNorms="true" positionIncrementGap="0" indexed="true" stored="false" />
136    <fieldType name="tlong" class="solr.TrieField" type="long" omitNorms="true" positionIncrementGap="0" indexed="true" stored="false" />
137    <fieldType name="tdouble" class="solr.TrieField" type="double" omitNorms="true" positionIncrementGap="0" indexed="true" stored="false" />
138
139    <fieldType name="tdouble4" class="solr.TrieField" type="double" precisionStep="4" omitNorms="true" positionIncrementGap="0" indexed="true" stored="false" />
140
141    <!--
142          This date field manipulates the value into a trie encoded strings for fast range searches. They follow the
143          same format and semantics as the normal DateField and support the date math syntax.
144    -->
145    <fieldType name="tdate" class="solr.TrieField" type="date" omitNorms="true" positionIncrementGap="0" indexed="true" stored="false" />
146
147
148    <!-- The "RandomSortField" is not used to store or search any
149         data.  You can declare fields of this type it in your schema
150         to generate psuedo-random orderings of your docs for sorting
151         purposes.  The ordering is generated based on the field name
152         and the version of the index, As long as the index version
153         remains unchanged, and the same field name is reused,
154         the ordering of the docs will be consistent. 
155         If you want differend psuedo-random orderings of documents,
156         for the same version of the index, use a dynamicField and
157         change the name
158     -->
159    <fieldType name="random" class="solr.RandomSortField" indexed="true" />
160
161    <!-- solr.TextField allows the specification of custom text analyzers
162         specified as a tokenizer and a list of token filters. Different
163         analyzers may be specified for indexing and querying.
164
165         The optional positionIncrementGap puts space between multiple fields of
166         this type on the same document, with the purpose of preventing false phrase
167         matching across fields.
168
169         For more info on customizing your analyzer chain, please see
170         http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
171     -->
172
173    <!-- One can also specify an existing Analyzer class that has a
174         default constructor via the class attribute on the analyzer element
175    <fieldType name="text_greek" class="solr.TextField">
176      <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
177    </fieldType>
178    -->
179
180    <!-- A text field that only splits on whitespace for exact matching of words -->
181    <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
182      <analyzer>
183        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
184      </analyzer>
185    </fieldType>
186
187
188        <!-- AHA, 2009-11-16: A tokenized text field without stemming (e.g. for person names) -->
189    <fieldType name="nostem" class="solr.TextField" positionIncrementGap="100">
190      <analyzer type="index">
191        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
192                <filter class="solr.ISOLatin1AccentFilterFactory"/>
193        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
194        <filter class="solr.LowerCaseFilterFactory"/>
195        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
196      </analyzer>
197      <analyzer type="query">
198        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
199                <filter class="solr.ISOLatin1AccentFilterFactory"/>
200        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
201        <filter class="solr.LowerCaseFilterFactory"/>
202        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
203      </analyzer>
204    </fieldType>
205
206
207
208    <!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
209        words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
210        so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
211        Synonyms and stopwords are customized by external files, and stemming is enabled.
212        Duplicate tokens at the same position (which may result from Stemmed Synonyms or
213        WordDelim parts) are removed.
214        -->
215    <fieldType name="text" class="solr.TextField" positionIncrementGap="100">
216      <analyzer type="index">
217        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
218        <!-- in this example, we will only use synonyms at query time
219        <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
220        -->
221        <!-- Case insensitive stop word removal.
222          add enablePositionIncrements=true in both the index and query
223          analyzers to leave a 'gap' for more accurate phrase queries.
224        -->
225        <filter class="solr.StopFilterFactory"
226                ignoreCase="true"
227                words="stopwords.txt"
228                enablePositionIncrements="true"
229                />
230                <filter class="solr.ISOLatin1AccentFilterFactory"/>
231        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
232        <filter class="solr.LowerCaseFilterFactory"/>
233        <!--<filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>-->
234                <filter class="solr.SnowballPorterFilterFactory" language="German"/>
235        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
236      </analyzer>
237      <analyzer type="query">
238        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
239        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
240        <filter class="solr.StopFilterFactory"
241                ignoreCase="true"
242                words="stopwords.txt"
243                enablePositionIncrements="true"
244                />
245                <filter class="solr.ISOLatin1AccentFilterFactory"/>
246        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
247        <filter class="solr.LowerCaseFilterFactory"/>
248        <!-- <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/> -->
249                <filter class="solr.SnowballPorterFilterFactory" language="German"/>
250        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
251      </analyzer>
252    </fieldType>
253
254
255    <!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
256         but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
257    <fieldType name="textTight" class="solr.TextField" positionIncrementGap="100" >
258      <analyzer>
259        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
260        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
261        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
262        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
263        <filter class="solr.LowerCaseFilterFactory"/>
264        <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
265        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
266      </analyzer>
267    </fieldType>
268
269    <!--
270     Setup simple analysis for spell checking
271     -->
272    <fieldType name="textSpell" class="solr.TextField" positionIncrementGap="100" >
273      <analyzer>
274        <tokenizer class="solr.StandardTokenizerFactory"/>
275        <filter class="solr.LowerCaseFilterFactory"/>
276        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
277      </analyzer>
278    </fieldType>
279
280    <!-- charFilter + "CharStream aware" WhitespaceTokenizer  -->
281    <!--
282    <fieldType name="textCharNorm" class="solr.TextField" positionIncrementGap="100" >
283      <analyzer>
284        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
285        <tokenizer class="solr.CharStreamAwareWhitespaceTokenizerFactory"/>
286      </analyzer>
287    </fieldType>
288    -->
289
290    <!-- This is an example of using the KeywordTokenizer along
291         With various TokenFilterFactories to produce a sortable field
292         that does not include some properties of the source text
293      -->
294    <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
295      <analyzer>
296        <!-- KeywordTokenizer does no actual tokenizing, so the entire
297             input string is preserved as a single token
298          -->
299        <tokenizer class="solr.KeywordTokenizerFactory"/>
300        <!-- The LowerCase TokenFilter does what you expect, which can be
301             when you want your sorting to be case insensitive
302          -->
303        <filter class="solr.LowerCaseFilterFactory" />
304        <!-- The TrimFilter removes any leading or trailing whitespace -->
305        <filter class="solr.TrimFilterFactory" />
306        <!-- The PatternReplaceFilter gives you the flexibility to use
307             Java Regular expression to replace any sequence of characters
308             matching a pattern with an arbitrary replacement string,
309             which may include back refrences to portions of the orriginal
310             string matched by the pattern.
311             
312             See the Java Regular Expression documentation for more
313             infomation on pattern and replacement string syntax.
314             
315             http://java.sun.com/j2se/1.5.0/docs/api/java/util/regex/package-summary.html
316          -->
317        <filter class="solr.PatternReplaceFilterFactory"
318                pattern="([^a-z])" replacement="" replace="all"
319        />
320      </analyzer>
321    </fieldType>
322   
323    <fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
324      <analyzer>
325        <tokenizer class="solr.StandardTokenizerFactory"/>
326        <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
327      </analyzer>
328    </fieldtype> 
329   
330
331    <!-- since fields of this type are by default not stored or indexed, any data added to
332         them will be ignored outright
333     --> 
334    <fieldtype name="ignored" stored="false" indexed="false" class="solr.StrField" /> 
335
336 </types>
337
338
339 <fields>
340   <!-- Valid attributes for fields:
341     name: mandatory - the name for the field
342     type: mandatory - the name of a previously defined type from the <types> section
343     indexed: true if this field should be indexed (searchable or sortable)
344     stored: true if this field should be retrievable
345     compressed: [false] if this field should be stored using gzip compression
346       (this will only apply if the field type is compressable; among
347       the standard field types, only TextField and StrField are)
348     multiValued: true if this field may contain multiple values per document
349     omitNorms: (expert) set to true to omit the norms associated with
350       this field (this disables length normalization and index-time
351       boosting for the field, and saves some memory).  Only full-text
352       fields or fields that need an index-time boost need norms.
353     termVectors: [false] set to true to store the term vector for a given field.
354       When using MoreLikeThis, fields used for similarity should be stored for
355       best performance.
356     termPositions: Store position information with the term vector.  This will increase storage costs.
357     termOffsets: Store offset information with the term vector. This will increase storage costs.
358   -->
359
360        <!-- Aufsatz- oder Buchtitel -->
361        <field name="title" type="text" indexed="true" stored="true" multiValued="false" termVectors="true" termPositions="true" termOffsets="true"/>
362        <!-- Sortierfeld des Aufsatz- oder Buchtitels -->
363        <field name="sorttitle" type="alphaOnlySort" indexed="true" stored="true" multiValued="false" omitNorms="true"/>
364        <!-- Paralleltitel -->
365        <field name="parallel_title" type="text" indexed="true" stored="true" multiValued="false" termVectors="true" termPositions="true" termOffsets="true"/>
366        <!-- Titelzusatz -->
367        <field name="titelzusatz" type="text" indexed="true" stored="true" multiValued="false"/>
368       
369        <!-- Verfasser -->
370        <field name="creator" type="nostem" indexed="true" stored="true" multiValued="true"/>
371        <!-- Sortierfeld fuer Verfasser/Herausgeber/Mitarbeiter -->
372        <field name="sperson" type="alphaOnlySort" indexed="true" stored="true" multiValued="false" omitNorms="true"/>
373        <!-- Herausgeber -->
374        <field name="editor" type="nostem" indexed="true" stored="true" multiValued="true"/>
375        <!-- Mitarbeiter -->
376        <field name="contributor" type="nostem" indexed="true" stored="true" multiValued="true"/>
377        <!-- Navigator fuer Verfasser/Herausgeber/Mitarbeiter -->
378        <field name="fperson" type="string" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
379        <!-- Feld für Personen in der erweiterten Suche -->
380        <field name="person" type="nostem" indexed="true" stored="true" multiValued="true"/>
381        <!-- Institution -->
382        <field name="institution" type="nostem" indexed="true" stored="true" multiValued="true"/>
383       
384        <!-- Freies Schlagwort -->
385        <field name="subject" type="text" indexed="true" stored="true" multiValued="true" termVectors="true"/>
386        <!-- Navigator fuer freies Schlagwort -->
387        <field name="fsubject" type="string" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
388        <!-- Schlagwortfeld fuer Tagcloud -->
389        <field name="tagcloud" type="string" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
390       
391        <!-- STW Deskriptor -->
392        <field name="stwdesc" type="string" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
393        <!-- STW Schlagwort -->
394        <field name="stwterm" type="string" indexed="true" stored="true" multiValued="true"/>
395       
396        <!-- Zeitschriftentitel -->
397        <field name="journal_title" type="text" indexed="true" stored="true"/>
398        <!-- Abgekuerzter Zeitschriftentitel (Haben wir sowas in der Hochschulbibliographie?)-->
399        <!--<field name="abbr_jtitle" type="string" indexed="true" stored="true"/>-->
400        <!-- Reihentitel -->
401        <field name="series_title" type="text" indexed="true" stored="true"/>
402        <!-- Zeitschriften-/Reihentitel-Navigator -->
403        <!-- mehrere Serientitel??? -->
404        <field name="fjtitle" type="string" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
405
406        <!-- Verlag -->
407        <field name="publisher" type="nostem" indexed="true" stored="true" multiValued="true"/>
408        <!-- Erscheinungsort -->
409        <field name="place" type="nostem" stored="true" multiValued="true" omitNorms="true"/>
410        <!-- Heft -->
411        <field name="issue" type="string" stored="true" omitNorms="true"/>
412        <!-- Jahrgang -->
413        <field name="volume" type="string" stored="true" omitNorms="true"/>
414        <!-- Seitenangaben -->
415        <field name="pages" type="string" stored="true" multiValued="true" omitNorms="true"/>
416        <!-- Ausgabe -->
417        <field name="edition" type="string" stored="true" omitNorms="true"/>
418        <!-- Anzahl der Baende -->
419        <field name="volumes" type="string" stored="true" omitNorms="true"/>
420       
421        <!-- Bibliothek -->
422        <field name="location" type="string" indexed="true" stored="true" multiValued="true"/>
423        <!-- Signatur -->
424        <field name="locator" type="string" stored="true" multiValued="true" omitNorms="true"/>
425        <!-- Standort ist die Kombination aus Bibliothek und Signatur -->
426        <field name="standort" type="string" stored="true" multiValued="true" omitNorms="true"/>
427
428        <!-- Erscheinungsjahr -->
429        <!-- Wg. Datumsbereichen von Herausgeberschaften nicht Typ "date"...-->
430        <field name="date" type="string" indexed="true" stored="true"/>
431        <!-- Datumsnavigator -->
432        <field name="fdate" type="string" indexed="true" stored="true" omitNorms="true"/>
433       
434        <!-- Exportfelder -->
435        <!-- MODS-Container -->
436        <field name="mods" type="string" indexed="false" stored="true" compressed="true"/>
437        <!-- Dublin Core Description Set-Container -->
438        <field name="dcds" type="string" indexed="false" stored="true" compressed="true"/>
439        <!-- BibTeX-Container -->
440        <field name="bibtex" type="string" indexed="false" stored="true" compressed="true"/>
441        <!-- RIS-Container -->
442        <field name="ris" type="string" indexed="false" stored="true" compressed="true"/>
443        <!-- Dublin Core fuer OAI-Container -->
444        <field name="dc" type="string" indexed="false" stored="true" compressed="true"/>
445        <!-- JSON-Container -->
446        <field name="json" type="string" indexed="false" stored="true" compressed="true"/>
447
448        <!-- Technische Metadaten -->
449        <!-- Zugriffs-ID -->
450        <field name="entryID" type="string" indexed="true" stored="true" omitNorms="true"/>
451        <!-- ID-URN fuer Feed -->
452        <field name="id" type="string" indexed="true" stored="true" omitNorms="true"/>
453        <!-- Disziplin -->
454        <field name="disziplin" type="string" indexed="true" stored="true" termVectors="true" termPositions="true" termOffsets="true"/>
455        <!-- Fakultaet -->
456        <field name="fakultaet" type="string" indexed="true" stored="true"/>
457        <!-- Zentrale Einheiten (z.B. UB, Research Departments etc.) -->
458        <field name="zentraleeinheit" type="string" indexed="true" stored="true"/>
459        <!-- Fach -->
460        <field name="fach" type="string" indexed="true" stored="true" termVectors="true" termPositions="true" termOffsets="true"/>
461        <!-- Erzeugungsdatum des Datensatzes -->
462        <field name="recordCreationDate" type="date" indexed="true" stored="true" omitNorms="true"/>
463        <!-- Aenderungsdatum des Datensatzes (fuer OAI) -->
464        <field name="recordChangeDate" type="date" indexed="true" stored="true" omitNorms="true"/>
465
466        <!-- Hierarchische Publikationstypen -->
467        <field name="genrel1" type="string" indexed="true" stored="true"/>
468        <field name="genrel2" type="string" indexed="true" stored="true"/>
469        <!-- Original Publikationsart, um Zeitschriften und Sammelwerke an der Oberflaeche
470        zusammenbauen zu koennen... (Brauchen wir das noch?)-->
471        <!--<field name="orig_genre" type="string" indexed="true" stored="true" omitNorms="true"/>-->
472        <!-- Format (Brauchen wir das ueberhaupt?)-->
473        <!--<field name="type" type="string" indexed="true" stored="true" omitNorms="true"/>-->
474        <!-- Sprache -->
475        <field name="language" type="string" indexed="true" stored="true" multiValued="true"/>
476
477        <!-- OpenURL-Zitation -->
478        <field name="bibliographicCitation" type="string" stored="true" omitNorms="true"/>
479        <!-- Inhaltsverzeichnis als URL -->
480        <field name="toc_link" type="string" stored="true" omitNorms="true"/>
481        <!-- Inhaltsverzeichnis als Text -->
482        <field name="toc_text" type="text" indexed="true" stored="true"/>
483       
484        <!-- Zusammenfassung -->
485        <field name="abstract" type="text" indexed="true" stored="true" multiValued="false" termVectors="true" termPositions="true" termOffsets="true"/>
486        <!-- Kommentar -->
487        <field name="note" type="text" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
488
489        <!-- ISSN -->
490        <field name="issn" type="string" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
491        <!-- ISBN -->
492        <field name="isbn" type="string" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
493        <!-- Sammelfeld fuer ISBN und ISSN in erweiterter Suche -->
494        <field name="isxn" type="string" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
495        <!-- DOI -->
496        <field name="doi" type="string" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
497        <!-- URN -->
498        <field name="urn" type="string" indexed="true" stored="true" multiValued="true" omitNorms="true"/>
499        <!-- URL -->
500        <field name="url" type="string" stored="true" multiValued="true" omitNorms="true"/>
501        <!-- WorldCat-URL -->
502        <field name="worldcat_url" type="string" stored="true" omitNorms="true"/>
503        <!-- Google Book-URL -->
504        <field name="google_book_url" type="string" stored="true" omitNorms="true"/>
505        <!-- Patent -->
506        <field name="patent_id" type="string" indexed="true" stored="true" omitNorms="true"/>
507        <!-- PND -->
508        <field name="pnd" type="string" indexed="true" stored="true" omitNorms="true" multiValued="true"/>
509        <!-- TicTocs -->
510        <field name="tictoc" type="string" stored="true" omitNorms="true" multiValued="true"/>
511        <!-- Impact Factor -->
512        <field name="jcr" type="string" stored="true" omitNorms="true" multiValued="true"/>
513       
514        <field name="other" type="ignored" multiValued="true"/>
515
516   <!-- catchall field, containing all other searchable text fields (implemented
517        via copyField further on in this schema  -->
518   <field name="text" type="text" indexed="true" stored="false" multiValued="true"/>
519
520
521   <!-- Some examples of trie fields -->
522   <!--<field name="tint" type="tint" indexed="true" stored="false" />
523   <field name="tfloat" type="tfloat" indexed="true" stored="false" />
524   <field name="tlong" type="tlong" indexed="true" stored="false" />
525   <field name="tdouble" type="tdouble" indexed="true" stored="false" />-->
526
527   <!-- A double with a custom precisionStep -->
528   <!--<field name="tdouble4" type="tdouble4" indexed="true" stored="false" />-->
529
530   <!-- An example for the trie date field -->
531   <!--<field name="tdate" type="tdate" indexed="true" stored="true" />-->
532
533   <!-- Dynamic field definitions.  If a field name is not found, dynamicFields
534        will be used if the name matches any of the patterns.
535        RESTRICTION: the glob-like pattern in the name attribute must have
536        a "*" only at the start or the end.
537        EXAMPLE:  name="*_i" will match any field ending in _i (like myid_i, z_i)
538        Longer patterns will be matched first.  if equal size patterns
539        both match, the first appearing in the schema will be used.  -->
540
541
542   <!-- uncomment the following to ignore any fields that don't already match an existing
543        field name or dynamic field, rather than reporting them as an error.
544        alternately, change the type="ignored" to some other type e.g. "text" if you want
545        unknown fields indexed and/or stored by default --> 
546   <!--dynamicField name="*" type="ignored" multiValued="true" /-->
547   
548 </fields>
549
550 <!-- Field to use to determine and enforce document uniqueness.
551      Unless this field is marked with required="false", it will be a required field
552   -->
553 <uniqueKey>entryID</uniqueKey>
554
555 <!-- field for the QueryParser to use when an explicit fieldname is absent -->
556 <defaultSearchField>text</defaultSearchField>
557
558 <!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
559 <solrQueryParser defaultOperator="AND"/>
560
561  <!-- copyField commands copy one field to another at the time a document
562        is added to the index.  It's used either to index the same field differently,
563        or to add multiple fields to the same field for easier/faster searching.  -->
564   <copyField source="creator" dest="text"/>
565   <copyField source="contributor" dest="text"/>
566   <copyField source="editor" dest="text"/>
567   <copyField source="publisher" dest="text"/>
568   <copyField source="title" dest="text"/>
569   <copyField source="titelzusatz" dest="text"/>
570   <copyField source="subject" dest="text"/>
571   <copyField source="journal_title" dest="text"/>
572   <copyField source="series_title" dest="text"/>
573   <copyField source="location" dest="text"/>
574   <copyField source="fdate" dest="text"/>
575   <copyField source="abstract" dest="text"/>
576   <copyField source="issn" dest="text"/>
577   <copyField source="isbn" dest="text"/>
578   <copyField source="stwdesc" dest="text"/>
579   <copyField source="stwterm" dest="text"/>
580
581 <!-- Similarity is the scoring routine for each document vs. a query.
582      A custom similarity may be specified here, but the default is fine
583      for most applications.  -->
584 <!-- <similarity class="org.apache.lucene.search.DefaultSimilarity"/> -->
585 <!-- ... OR ...
586      Specify a SimilarityFactory class name implementation
587      allowing parameters to be used.
588 -->
589 <!--
590 <similarity class="com.example.solr.CustomSimilarityFactory">
591   <str name="paramkey">param value</str>
592 </similarity>
593 -->
594
595
596</schema>
Note: See TracBrowser for help on using the repository browser.