weather.xml

<?xml version="1.0" encoding="UTF-8" ?>
<!--
  Licensed to the Apache Software Foundation (ASF) under one or more
  contributor license agreements.  See the NOTICE file distributed with
  this work for additional information regarding copyright ownership.
  The ASF licenses this file to You under the Apache License, Version 2.0
  (the "License"); you may not use this file except in compliance with
  the License.  You may obtain a copy of the License at

      http://www.apache.org/licenses/LICENSE-2.0

  Unless required by applicable law or agreed to in writing, software
  distributed under the License is distributed on an "AS IS" BASIS,
  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  See the License for the specific language governing permissions and
  limitations under the License.
-->

<schema name="weather" version="1.5">
  <fields>

    <!-- custom fields -->
    <field name="q" type="search_pt" indexed="true" stored="false" multiValued="true"/>

    <field name="price" type="currency" indexed="true" stored="true" multiValued="false" omitNorms="true"/>
    <field name="datetime" type="tdate" indexed="true" stored="false" multiValued="false" omitNorms="true"/>

    <field name="temp_hi_register" type="tint" indexed="true" stored="true" multiValued="false" omitNorms="true"/>
    <field name="temp_lo_register" type="tint" indexed="true" stored="true" multiValued="false" omitNorms="true"/>

    <field name="prcp_register" type="tfloat" indexed="true" stored="true" multiValued="false" omitNorms="true"/>

    <!-- available types  -->

   <field name="_version_" type="long" indexed="true" stored="true"/>

   <field name="text" type="text_general" indexed="true" stored="false" multiValued="true"/>

   <dynamicField name="*_i"  type="int"    indexed="true"  stored="true"  multiValued="false"/>
   <dynamicField name="*_is" type="int"    indexed="true"  stored="true"  multiValued="true"/>
   <dynamicField name="*_l"  type="long"   indexed="true"  stored="true"  multiValued="false"/>
   <dynamicField name="*_ls" type="long"   indexed="true"  stored="true"  multiValued="true"/>
   <dynamicField name="*_d"  type="double" indexed="true"  stored="true"  multiValued="false"/>
   <dynamicField name="*_ds" type="double" indexed="true"  stored="true"  multiValued="true"/>
   <dynamicField name="*_f"  type="float"  indexed="true"  stored="true"  multiValued="false"/>
   <dynamicField name="*_fs" type="float"  indexed="true"  stored="true"  multiValued="true"/>

   <dynamicField name="*_s"  type="string"  indexed="true"  stored="true" multiValued="false"/>
   <dynamicField name="*_ss" type="string"  indexed="true"  stored="true" multiValued="true"/>

   <dynamicField name="*_t"  type="text_general" indexed="true"  stored="false" multiValued="false"/>
   <dynamicField name="*_ts" type="text_general" indexed="true"  stored="false" multiValued="true"/>

   <dynamicField name="*_tsd" type="text_general" indexed="true" stored="true" multiValued="false"/>
   <dynamicField name="*_tssd" type="text_general" indexed="true" stored="true" multiValued="true"/>

   <!-- languages -->
   <dynamicField name="*_pt" type="text_pt" indexed="true" stored="true" multiValued="true"/>

   <dynamicField name="*_b"  type="boolean" indexed="true" stored="true" multiValued="false"/>
   <dynamicField name="*_bs" type="boolean" indexed="true" stored="true"  multiValued="true"/>
   <dynamicField name="*_dt"  type="date"    indexed="true"  stored="true" multiValued="false"/>
   <dynamicField name="*_dts" type="date"    indexed="true"  stored="true" multiValued="true"/>
   <dynamicField name="*_coordinate"  type="tdouble" indexed="true"  stored="false" multiValued="false"/>
   <dynamicField name="*_p" type="location" indexed="true" stored="true" multiValued="false"/>

   <!-- some trie-coded dynamic fields for faster range queries -->
   <dynamicField name="*_ti" type="tint"    indexed="true"  stored="true" multiValued="false"/>
   <dynamicField name="*_tl" type="tlong"   indexed="true"  stored="true" multiValued="false"/>
   <dynamicField name="*_tf" type="tfloat"  indexed="true"  stored="true" multiValued="false"/>
   <dynamicField name="*_td" type="tdouble" indexed="true"  stored="true" multiValued="false"/>
   <dynamicField name="*_tdt" type="tdate"  indexed="true"  stored="true" multiValued="false"/>

   <dynamicField name="*_ig" type="ignored" multiValued="true"/>
   <dynamicField name="random_*" type="random" />

   <!-- Riak datatypes embedded fields -->
   <dynamicField name="*_flag"     type="boolean" indexed="true" stored="true" multiValued="false"/>
   <dynamicField name="*_counter"  type="int"     indexed="true" stored="true" multiValued="false"/>
   <dynamicField name="*_register" type="string"  indexed="true" stored="true" multiValued="false"/>
   <dynamicField name="*_set"      type="string"  indexed="true" stored="true" multiValued="true"/>

   <!-- catch-all field -->
   <dynamicField name="*" type="ignored" />

   <field name="_yz_id" type="_yz_str" indexed="true" stored="true" multiValued="false" required="true"/>

   <!-- Entropy Data: Data related to anti-entropy -->
   <field name="_yz_ed" type="_yz_str" indexed="true" stored="false" multiValued="false"/>

   <!-- Partition Number: Used as a filter query param -->
   <field name="_yz_pn" type="_yz_str" indexed="true" stored="false" multiValued="false"/>

   <!-- First Partition Number: The first partition in this doc's
        preflist, used for further filtering on overlapping partitions. -->
   <field name="_yz_fpn" type="_yz_str" indexed="true" stored="false" multiValued="false"/>

   <!-- If there is a sibling, use vtag to differentiate them -->
   <field name="_yz_vtag" type="_yz_str" indexed="true" stored="false" multiValued="false"/>

   <!-- Riak Key: The key of the Riak object this doc corresponds to. -->
   <field name="_yz_rk" type="_yz_str" indexed="true" stored="true" multiValued="false"/>

   <!-- Riak Bucket Type: The bucket type of the Riak object this doc corresponds to. -->
   <field name="_yz_rt" type="_yz_str" indexed="true" stored="true" multiValued="false"/>

   <!-- Riak Bucket: The bucket of the Riak object this doc corresponds to. -->
   <field name="_yz_rb" type="_yz_str" indexed="true" stored="true" multiValued="false"/>

   <!-- Flag indicating if this doc is the product of a failed object extraction -->
   <field name="_yz_err" type="_yz_str" indexed="true" stored="false" multiValued="false"/>
 </fields>

 <!-- copy fields-->
 <copyField source="*_register" dest="q"/>
 <copyField source="prcp_register" dest="price"/>
 <copyField source="updated_at_register" dest="datetime"/>

 <!-- document id is mandatory -->
 <uniqueKey>_yz_id</uniqueKey>

 <types>
   <!-- YZ String: Used for non-analyzed fields -->
   <fieldType name="_yz_str" class="solr.StrField" sortMissingLast="true" />

   <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
   <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>

   <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"/>

   <fieldType name="currency" class="solr.CurrencyField"
              precisionStep="8" currencyConfig="currency.xml" defaultCurrency="AOA" />
   <!--
       Numeric field types that index each value at various levels of precision
       to accelerate range queries when the number of values between the range
       endpoints is large. See the javadoc for NumericRangeQuery for internal
       implementation details.

       Smaller precisionStep values (specified in bits) will lead to more tokens
       indexed per value, slightly larger index size, and faster range queries.
       A precisionStep of 0 disables indexing at different precision levels.
   -->
   <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
   <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
   <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
   <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>

   <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"/>

   <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
   <fieldtype name="binary" class="solr.BinaryField"/>

   <fieldType name="random" class="solr.RandomSortField" indexed="true" />

   <!-- Portuguese Search -->
   <fieldType name="search_pt" class="solr.TextField" positionIncrementGap="100" omitNorms="true">
     <analyzer type="index">
       <tokenizer class="solr.StandardTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
       <filter class="solr.PortugueseLightStemFilterFactory"/>
       <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
       <filter class="solr.EdgeNGramFilterFactory" minGramSize="2" maxGramSize="25"/>
       <filter class="solr.ReverseStringFilterFactory" />
       <filter class="solr.EdgeNGramFilterFactory" minGramSize="2" maxGramSize="25"/>
       <filter class="solr.ReverseStringFilterFactory" />
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.StandardTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
       <filter class="solr.PortugueseLightStemFilterFactory"/>
       <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
     </analyzer>
   </fieldType>
<!--
       <tokenizer class="solr.StandardTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
       <filter class="solr.PortugueseLightStemFilterFactory"/>
       <filter class="solr.TrimFilterFactory" />
       <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       <filter class="solr.EdgeNGramFilterFactory" minGramSize="1" maxGramSize="10" side="front" />
       <filter class="solr.EdgeNGramFilterFactory" minGramSize="1" maxGramSize="10" side="back" />
-->
<!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
       <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
       <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->

   <!-- 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" />
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.StandardTokenizerFactory"/>
       <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
       <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
   </fieldType>

   <!-- A text field with defaults appropriate for English: it
        tokenizes with StandardTokenizer, removes English stop words
        (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"/>
       <filter class="solr.StopFilterFactory"
               ignoreCase="true"
               words="lang/stopwords_en.txt"
               />
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.EnglishPossessiveFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
       <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"
               />
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.EnglishPossessiveFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
       <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"/>
       <filter class="solr.StopFilterFactory"
               ignoreCase="true"
               words="lang/stopwords_en.txt"
               />
       <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"
               />
       <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"/>
       <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" />
       <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" />
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
   </fieldType>

   <!-- charFilter + WhitespaceTokenizer  -->
   <!--
       <fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
       <analyzer>
       <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
       <tokenizer class="solr.WhitespaceTokenizerFactory"/>
       </analyzer>
       </fieldType>
   -->

   <!-- This is an example of using the KeywordTokenizer along
        With various TokenFilterFactories to produce a sortable field
        that does not include some properties of the source text
   -->
   <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
     <analyzer>
       <!-- KeywordTokenizer does no actual tokenizing, so the entire
            input string is preserved as a single token
       -->
       <tokenizer class="solr.KeywordTokenizerFactory"/>
       <!-- The LowerCase TokenFilter does what you expect, which can be
            when you want your sorting to be case insensitive
       -->
       <filter class="solr.LowerCaseFilterFactory" />
       <!-- The TrimFilter removes any leading or trailing whitespace -->
       <filter class="solr.TrimFilterFactory" />
       <!-- The PatternReplaceFilter gives you the flexibility to use
            Java Regular expression to replace any sequence of characters
            matching a pattern with an arbitrary replacement string,
            which may include back references to portions of the original
            string matched by the pattern.

            See the Java Regular Expression documentation for more
            information on pattern and replacement string syntax.

            http://java.sun.com/j2se/1.6.0/docs/api/java/util/regex/package-summary.html
       -->
       <filter class="solr.PatternReplaceFilterFactory"
               pattern="([^a-z])" replacement="" replace="all"
               />
     </analyzer>
   </fieldType>

   <fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
     <analyzer>
       <tokenizer class="solr.StandardTokenizerFactory"/>
       <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
     </analyzer>
   </fieldtype>

   <fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
     <analyzer>
       <tokenizer class="solr.WhitespaceTokenizerFactory"/>
       <!--
           The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
           a token of "foo|1.4"  would be indexed as "foo" with a payload of 1.4f
           Attributes of the DelimitedPayloadTokenFilterFactory :
           "delimiter" - a one character delimiter. Default is | (pipe)
           "encoder" - how to encode the following value into a playload
           float -> org.apache.lucene.analysis.payloads.FloatEncoder,
           integer -> o.a.l.a.p.IntegerEncoder
           identity -> o.a.l.a.p.IdentityEncoder
           Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
       -->
       <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
     </analyzer>
   </fieldtype>

   <!-- lowercases the entire field value, keeping it as a single token.  -->
   <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
     <analyzer>
       <tokenizer class="solr.KeywordTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory" />
     </analyzer>
   </fieldType>

   <fieldType name="text_path" class="solr.TextField" positionIncrementGap="100">
     <analyzer>
       <tokenizer class="solr.PathHierarchyTokenizerFactory"/>
     </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" />

   <!-- This point type indexes the coordinates as separate fields (subFields)
        If subFieldType is defined, it references a type, and a dynamic field
        definition is created matching *___<typename>.  Alternately, if
        subFieldSuffix is defined, that is used to create the subFields.
        Example: if subFieldType="double", then the coordinates would be
        indexed in fields myloc_0___double,myloc_1___double.
        Example: if subFieldSuffix="_d" then the coordinates would be indexed
        in fields myloc_0_d,myloc_1_d
        The subFields are an implementation detail of the fieldType, and end
        users normally should not need to know about them.
   -->
   <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>

   <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
   <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>

   <!--
       A Geohash is a compact representation of a latitude longitude pair in a single field.
       See http://wiki.apache.org/solr/SpatialSearch
   -->
   <fieldtype name="geohash" class="solr.GeoHashField"/>

   <!-- some examples for different languages (generally ordered by ISO code) -->

   <!-- Portuguese -->
   <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
     <analyzer>
       <tokenizer class="solr.StandardTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
       <filter class="solr.PortugueseLightStemFilterFactory"/>
       <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
       <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
       <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
     </analyzer>
   </fieldType>
 </types>

</schema>