tools/scripts/solr/schema.xml

   1 <?xml version="1.0" ?>
   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 <!-- This is the Solr schema file. This file should be named "schema.xml" and
  20  should be in the conf directory under the solr home
  21  (i.e. ./solr/conf/schema.xml by default)
  22  or located where the classloader for the Solr webapp can find it.
  23
  24  For more information, on how to customize this file, please see
  25  http://wiki.apache.org/solr/SchemaXml
  26 -->
  27
  28 <schema name="civicrm_contact" version="1.1">
  29   <!-- attribute "name" is the name of this schema and is only used for display purposes.
  30        Applications should change this to reflect the nature of the search collection.
  31        version="1.1" is Solr's version number for the schema syntax and semantics.  It should
  32        not normally be changed by applications.
  33        1.0: multiValued attribute did not exist, all fields are multiValued by nature
  34        1.1: multiValued attribute introduced, false by default -->
  35
  36   <types>
  37     <!-- field type definitions. The "name" attribute is
  38        just a label to be used by field definitions.  The "class"
  39        attribute and any other attributes determine the real
  40        behavior of the fieldtype.
  41          Class names starting with "solr" refer to java classes in the
  42        org.apache.solr.analysis package.
  43     -->
  44
  45     <!-- The StrField type is not analyzed, but indexed/stored verbatim.
  46        - StrField and TextField support an optional compressThreshold which
  47        limits compression (if enabled in the derived fields) to values which
  48        exceed a certain size (in characters).
  49     -->
  50     <fieldtype name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
  51
  52     <!-- boolean type: "true" or "false" -->
  53     <fieldtype name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
  54
  55     <!-- The optional sortMissingLast and sortMissingFirst attributes are
  56          currently supported on types that are sorted internally as strings.
  57        - If sortMissingLast="true", then a sort on this field will cause documents
  58          without the field to come after documents with the field,
  59          regardless of the requested sort order (asc or desc).
  60        - If sortMissingFirst="true", then a sort on this field will cause documents
  61          without the field to come before documents with the field,
  62          regardless of the requested sort order.
  63        - If sortMissingLast="false" and sortMissingFirst="false" (the default),
  64          then default lucene sorting will be used which places docs without the
  65          field first in an ascending sort and last in a descending sort.
  66     -->
  67
  68
  69     <!-- numeric field types that store and index the text
  70          value verbatim (and hence don't support range queries, since the
  71          lexicographic ordering isn't equal to the numeric ordering) -->
  72     <fieldtype name="integer" class="solr.IntField" omitNorms="true"/>
  73     <fieldtype name="long" class="solr.LongField" omitNorms="true"/>
  74     <fieldtype name="float" class="solr.FloatField" omitNorms="true"/>
  75     <fieldtype name="double" class="solr.DoubleField" omitNorms="true"/>
  76
  77
  78     <!-- Numeric field types that manipulate the value into
  79          a string value that isn't human-readable in its internal form,
  80          but with a lexicographic ordering the same as the numeric ordering,
  81          so that range queries work correctly. -->
  82     <fieldtype name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/>
  83     <fieldtype name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/>
  84     <fieldtype name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/>
  85     <fieldtype name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/>
  86
  87
  88     <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
  89          is a more restricted form of the canonical representation of dateTime
  90          http://www.w3.org/TR/xmlschema-2/#dateTime
  91          The trailing "Z" designates UTC time and is mandatory.
  92          Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
  93          All other components are mandatory.
  94
  95          Expressions can also be used to denote calculations that should be
  96          performed relative to "NOW" to determine the value, ie...
  97
  98                NOW/HOUR
  99                   ... Round to the start of the current hour
 100                NOW-1DAY
 101                   ... Exactly 1 day prior to now
 102                NOW/DAY+6MONTHS+3DAYS
 103                   ... 6 months and 3 days in the future from the start of
 104                       the current day
 105
 106          Consult the DateField javadocs for more information.
 107       -->
 108     <fieldtype name="date" class="solr.DateField" sortMissingLast="true" omitNorms="true"/>
 109
 110     <!-- solr.TextField allows the specification of custom text analyzers
 111          specified as a tokenizer and a list of token filters. Different
 112          analyzers may be specified for indexing and querying.
 113
 114          The optional positionIncrementGap puts space between multiple fields of
 115          this type on the same document, with the purpose of preventing false phrase
 116          matching across fields.
 117
 118          For more info on customizing your analyzer chain, please see
 119          http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
 120      -->
 121
 122     <!-- One can also specify an existing Analyzer class that has a
 123          default constructor via the class attribute on the analyzer element
 124     <fieldtype name="text_greek" class="solr.TextField">
 125       <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
 126     </fieldType>
 127     -->
 128
 129     <!-- A text field that only splits on whitespace for exact matching of words -->
 130     <fieldtype name="text_ws" class="solr.TextField" positionIncrementGap="100">
 131       <analyzer>
 132         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
 133       </analyzer>
 134     </fieldtype>
 135
 136     <!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
 137         words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
 138         so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
 139         Synonyms and stopwords are customized by external files, and stemming is enabled.
 140         Duplicate tokens at the same position (which may result from Stemmed Synonyms or
 141         WordDelim parts) are removed.
 142         -->
 143     <fieldtype name="text" class="solr.TextField" positionIncrementGap="100">
 144       <analyzer type="index">
 145         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
 146         <!-- in this example, we will only use synonyms at query time
 147         <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
 148         -->
 149         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
 150         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
 151         <filter class="solr.LowerCaseFilterFactory"/>
 152         <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
 153         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
 154       </analyzer>
 155       <analyzer type="query">
 156         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
 157         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
 158         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
 159         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
 160         <filter class="solr.LowerCaseFilterFactory"/>
 161         <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
 162         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
 163       </analyzer>
 164     </fieldtype>
 165
 166
 167     <!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
 168          but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
 169     <fieldtype name="textTight" class="solr.TextField" positionIncrementGap="100" >
 170       <analyzer>
 171         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
 172         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
 173         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
 174         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
 175         <filter class="solr.LowerCaseFilterFactory"/>
 176         <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
 177         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
 178       </analyzer>
 179     </fieldtype>
 180
 181  </types>
 182
 183
 184  <fields>
 185    <!-- Valid attributes for fields:
 186      name: mandatory - the name for the field
 187      type: mandatory - the name of a previously defined type from the <types> section
 188      indexed: true if this field should be indexed (searchable or sortable)
 189      stored: true if this field should be retrievable
 190      compressed: [false] if this field should be stored using gzip compression
 191        (this will only apply if the field type is compressable; among
 192        the standard field types, only TextField and StrField are)
 193      multiValued: true if this field may contain multiple values per document
 194      omitNorms: (expert) set to true to omit the norms associated with
 195        this field (this disables length normalization and index-time
 196        boosting for the field, and saves some memory).  Only full-text
 197        fields or fields that need an index-time boost need norms.
 198    -->
 199
 200    <field name="id"                     type="sint" indexed="true" stored="true" />
 201
 202    <!-- fields from civicrm_contact -->
 203    <field name="sort_name"              type="text" indexed="true" stored="true" />
 204    <field name="display_name"           type="text" indexed="true" stored="true" />
 205    <field name="nick_name"              type="text" indexed="true" stored="false"/>
 206    <field name="legal_identifier"       type="text" indexed="true" stored="false"/>
 207    <field name="external_identifier"    type="text" indexed="true" stored="false"/>
 208    <field name="contact_source"         type="text" indexed="true" stored="false"/>
 209    <field name="contact_type"           type="text" indexed="true" stored="false"/>
 210
 211    <!-- fields from civicrm_individual -->
 212    <field name="first_name"             type="text" indexed="true" stored="false"/>
 213    <field name="last_name"              type="text" indexed="true" stored="false"/>
 214    <field name="middle_name"            type="text" indexed="true" stored="false"/>
 215    <field name="job_title"              type="text" indexed="true" stored="false"/>
 216    <field name="birth_date"             type="date" indexed="true" stored="false"/>
 217    <field name="deceased_date"          type="date" indexed="true" stored="false"/>
 218    <field name="gender"                 type="text" indexed="true" stored="false"/>
 219
 220    <!-- fields from civicrm_household -->
 221    <field name="household_name"         type="text" indexed="true" stored="false"/>
 222
 223    <!-- fields from civicrm_organization -->
 224    <field name="organization_name"      type="text" indexed="true" stored="false"/>
 225    <field name="legal_name"             type="text" indexed="true" stored="false"/>
 226    <field name="sic_code"               type="text" indexed="true" stored="false"/>
 227
 228    <!-- fields from civicrm_location, civicrm_address, civicrm_phone, civicrm_email -->
 229    <field name="location_name"          type="text" indexed="true" stored="false" multiValued="true"/>
 230    <field name="street_address"         type="text" indexed="true" stored="false" multiValued="true"/>
 231    <field name="supplemental_address_1" type="text" indexed="true" stored="false" multiValued="true"/>
 232    <field name="supplemental_address_2" type="text" indexed="true" stored="false" multiValued="true"/>
 233    <field name="supplemental_address_3" type="text" indexed="true" stored="false" multiValued="true"/>
 234    <field name="city"                   type="text" indexed="true" stored="false" multiValued="true"/>
 235
 236    <field name="county"                 type="text" indexed="true" stored="false" multiValued="true"/>
 237    <field name="state"                  type="text" indexed="true" stored="false" multiValued="true"/>
 238    <field name="postal_code"            type="text" indexed="true" stored="false" multiValued="true"/>
 239    <field name="country"                type="text" indexed="true" stored="false" multiValued="true"/>
 240    <field name="location_note"          type="text" indexed="true" stored="false" multiValued="true"/>
 241    <field name="email"                  type="text" indexed="true" stored="false" multiValued="true"/>
 242    <field name="phone"                  type="text" indexed="true" stored="false" multiValued="true"/>
 243    <field name="im"                     type="text" indexed="true" stored="false" multiValued="true"/>
 244
 245    <field name="note_subject"           type="text" indexed="true" stored="false" multiValued="true"/>
 246    <field name="note_body"              type="text" indexed="true" stored="false" multiValued="true"/>
 247
 248    <!-- catchall field, containing all other searchable text fields (implemented
 249         via copyField further on in this schema  -->
 250    <field name="text"    type="text" indexed="true" stored="false" multiValued="true"/>
 251    <field name="address" type="text" indexed="true" stored="false" multiValued="true"/>
 252    <field name="note"    type="text" indexed="true" stored="false" multiValued="true"/>
 253
 254    <!-- Dynamic field definitions.  If a field name is not found, dynamicFields
 255         will be used if the name matches any of the patterns.
 256         RESTRICTION: the glob-like pattern in the name attribute must have
 257         a "*" only at the start or the end.
 258         EXAMPLE:  name="*_i" will match any field ending in _i (like myid_i, z_i)
 259         Longer patterns will be matched first.  if equal size patterns
 260         both match, the first appearing in the schema will be used.  -->
 261    <dynamicField name="*_i"  type="sint"    indexed="true"  stored="true"/>
 262    <dynamicField name="*_s"  type="string"  indexed="true"  stored="true"/>
 263    <dynamicField name="*_l"  type="slong"   indexed="true"  stored="true"/>
 264    <dynamicField name="*_t"  type="text"    indexed="true"  stored="true"/>
 265    <dynamicField name="*_b"  type="boolean" indexed="true"  stored="true"/>
 266    <dynamicField name="*_f"  type="sfloat"  indexed="true"  stored="true"/>
 267    <dynamicField name="*_d"  type="sdouble" indexed="true"  stored="true"/>
 268    <dynamicField name="*_dt" type="date"    indexed="true"  stored="true"/>
 269  </fields>
 270
 271  <!-- field to use to determine and enforce document uniqueness. -->
 272  <uniqueKey>id</uniqueKey>
 273
 274  <!-- field for the QueryParser to use when an explicit fieldname is absent -->
 275  <defaultSearchField>text</defaultSearchField>
 276
 277  <!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
 278  <solrQueryParser defaultOperator="OR"/>
 279
 280   <!-- copyField commands copy one field to another at the time a document
 281         is added to the index.  It's used either to index the same field differently,
 282         or to add multiple fields to the same field for easier/faster searching.  -->
 283    <copyField source="note_subject"           dest="note"/>
 284    <copyField source="note_body"              dest="note"/>
 285
 286    <copyField source="street_address"         dest="address"/>
 287    <copyField source="supplemental_address_1" dest="address"/>
 288    <copyField source="supplemental_address_2" dest="address"/>
 289    <copyField source="supplemental_address_3" dest="address"/>
 290    <copyField source="city"                   dest="address"/>
 291    <copyField source="county"                 dest="address"/>
 292    <copyField source="state"                  dest="address"/>
 293    <copyField source="postal_code"            dest="address"/>
 294    <copyField source="country"                dest="address"/>
 295    <copyField source="location_note"          dest="address"/>
 296    <copyField source="email"                  dest="address"/>
 297    <copyField source="phone"                  dest="address"/>
 298    <copyField source="im"                     dest="address"/>
 299
 300    <copyField source="sort_name"              dest="text"/>
 301    <copyField source="nick_name"              dest="text"/>
 302    <copyField source="legal_identifier"       dest="text"/>
 303    <copyField source="external_identifier"    dest="text"/>
 304    <copyField source="contact_source"         dest="text"/>
 305    <copyField source="job_title"              dest="text"/>
 306    <copyField source="household_name"         dest="text"/>
 307    <copyField source="legal_name"             dest="text"/>
 308    <copyField source="sic_code"               dest="text"/>
 309    <copyField source="note_subject"           dest="text"/>
 310    <copyField source="note_body"              dest="text"/>
 311    <copyField source="street_address"         dest="text"/>
 312    <copyField source="supplemental_address_1" dest="text"/>
 313    <copyField source="supplemental_address_2" dest="text"/>
 314    <copyField source="supplemental_address_3" dest="text"/>
 315    <copyField source="city"                   dest="text"/>
 316    <copyField source="county"                 dest="text"/>
 317    <copyField source="state"                  dest="text"/>
 318    <copyField source="postal_code"            dest="text"/>
 319    <copyField source="country"                dest="text"/>
 320    <copyField source="location_note"          dest="text"/>
 321    <copyField source="email"                  dest="text"/>
 322    <copyField source="phone"                  dest="text"/>
 323    <copyField source="im"                     dest="text"/>
 324
 325
 326  <!-- Similarity is the scoring routine for each document vs. a query.
 327       A custom similarity may be specified here, but the default is fine
 328       for most applications.  -->
 329  <!-- <similarity class="org.apache.lucene.search.DefaultSimilarity"/> -->
 330
 331 </schema>