Solr schema.xml定义

项目中的经验之谈！2017-11-07 10:43:17

下面是搜索中定义的solr 的schema.xml 

1. 店铺schema.xml

<?xml version="1.0" encoding="UTF-8" ?>
<schema name="car" version="1.6">
   <field name="_version_" type="long" indexed="true" stored="false" />  
   <field name="_root_" type="string" indexed="true" stored="false" docValues="false" />

   <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" /> 
  <!-- 省份id =============begin 没有使用========= -->
   <field name="province_id" type="int" indexed="true" stored="true" required="false" multiValued="false" />
   <!-- 省份名 -->
   <field name="province" type="string" indexed="true" stored="true" required="false" multiValued="false" />
   <!-- 城市id -->
   <field name="city_id" type="int" indexed="true" stored="true" required="false" multiValued="false" />
    <!-- 市名 -->
   <field name="city" type="string" indexed="true" stored="true" required="false" multiValued="false" />
    <!-- 区域id -->
   <field name="area_id" type="int" indexed="true" stored="true" required="false" multiValued="false" />
   <!-- 区域id  =============end============     -->
   <field name="area" type="string" indexed="true" stored="true" required="false" multiValued="false" />
    <!-- 店铺id -->
   <field name="shop_id" type="int" indexed="true" stored="true" required="false" multiValued="false" />
   <!-- 店铺 -->
   <field name="shop" type="text_ik" indexed="true" stored="true" required="false" multiValued="false" />
   <!-- 门店ID -->
   <field name="store_id" type="string" indexed="true" stored="true" required="false" multiValued="false" />
    <!-- 店铺主图 -->
   <field name="shop_img" type="string" indexed="true" stored="true" required="false" multiValued="false" />
   <!-- 店铺经纬度 -->
   <field name="shop_location" type="location_rpt" indexed="true" stored="true" required="false" multiValued="false" omitNorms="true" />
   <!-- 店铺所在地 -->
   <field name="shop_coordinate" type="string" indexed="true" stored="true" required="false" multiValued="false" />
   <!-- 店铺星级 -->
   <field name="shop_level" type="string" indexed="true" stored="true" required="false" multiValued="false" />
   <!-- 联系方式 -->
   <field name="contact" type="string" indexed="true" stored="true" required="false" multiValued="false" />
   <!-- 是否是店铺 -->
   <field name="is_shop" type="boolean" indexed="true" stored="true" required="true" multiValued="false" />
   <field name="score" type="string" indexed="true" stored="true" required="false" multiValued="false" />
   <field name="dist" type="string" indexed="true" stored="true" required="false" multiValued="false" />
   <!-- 品牌 -->
   <field name="shop_brands" type="string" indexed="true" stored="true" required="false" multiValued="true" />
    <!-- 三级分类id -->
   <field name="category_third_ids" type="string" indexed="true" stored="true" required="false" multiValued="true" />
   <!-- 三级分类名 -->
   <field name="category_thirds" type="string" indexed="true" stored="true" required="false" multiValued="true" />
    <!-- 属性名 -->
   <field name="attr_name" type="string" indexed="true" stored="true" required="false" multiValued="true" />
   <!--  创建时间 -->
   <field name="create_time" type="date" indexed="false" stored="false" required="false" multiValued="false" />
   <!-- 过期时间 -->
   <field name="valid_time" type="date" indexed="false" stored="false" required="false" multiValued="false" />
   <!--  最后更新时间 -->
   <field name="last_modified" type="date" indexed="true" stored="false" required="false" multiValued="false" />
   
   
   <!-- 默认搜索域 将所有文本域放入里面。必须让mutiValued为true  多值-->
   <field name="text" type="text_ik" indexed="true" stored="false" multiValued="true"/>
  
 
   <!-- Dynamic field definitions allow using convention over configuration
       for fields via the specification of patterns to match field names. 
       EXAMPLE:  name="*_i" will match any field ending in _i (like myid_i, z_i)
       RESTRICTION: the glob-like pattern in the name attribute must have
       a "*" only at the start or the end.  -->
    <!-- 所有_id的域走此动态域，方便动态增加-->
   <dynamicField name="*_id"  type="int"    indexed="true"  stored="true"/>
   <!-- 所有_ch的域都使用ik进行分词-->
   <dynamicField name="*_ch"  type="text_ik"    indexed="true"  stored="true"/>
   <dynamicField name="*_i"  type="int"    indexed="true"  stored="true"/>
   <dynamicField name="*_is" type="int"    indexed="true"  stored="true"  multiValued="true"/>
   <dynamicField name="*_s"  type="string"  indexed="true"  stored="true" />
   <dynamicField name="*_ss" type="string"  indexed="true"  stored="true" multiValued="true"/>
   <dynamicField name="*_l"  type="long"   indexed="true"  stored="true"/>
   <dynamicField name="*_ls" type="long"   indexed="true"  stored="true"  multiValued="true"/>
   <dynamicField name="*_t"  type="text_general"    indexed="true"  stored="true"/>
   <dynamicField name="*_txt" type="text_general"   indexed="true"  stored="true" multiValued="true"/>
   <dynamicField name="*_en" type="text_en"    indexed="true"  stored="true" multiValued="true"/>
   <dynamicField name="*_b"  type="boolean" indexed="true" stored="true"/>
   <dynamicField name="*_bs" type="boolean" indexed="true" stored="true"  multiValued="true"/>
   <dynamicField name="*_f"  type="float"  indexed="true"  stored="true"/>
   <dynamicField name="*_fs" type="float"  indexed="true"  stored="true"  multiValued="true"/>
   <dynamicField name="*_d"  type="double" indexed="true"  stored="true"/>
   <dynamicField name="*_ds" type="double" indexed="true"  stored="true"  multiValued="true"/>

   <!-- Type used to index the lat and lon components for the "location" FieldType -->
   <dynamicField name="*_coordinate"  type="tdouble" indexed="true"  stored="false" useDocValuesAsStored="false" />

   <dynamicField name="*_dt"  type="date"    indexed="true"  stored="true"/>
   <dynamicField name="*_dts" type="date"    indexed="true"  stored="true" multiValued="true"/>
   <dynamicField name="*_p"  type="location" indexed="true" stored="true"/>

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

   <dynamicField name="*_c"   type="currency" indexed="true"  stored="true"/>

   <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
   <!--商品属性拓展字段-->
   <dynamicField name="*_attr" type="string" indexed="true" stored="true" multiValued="true"/>
  <dynamicField name="*_attr_c" type="text_ik" indexed="true" stored="false" multiValued="true"/>

   <dynamicField name="random_*" type="random" />
  <dynamicField name="*_brand" type="string" indexed="true" stored="true" multiValued="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" /-->
     
   <!--<copyField source="*_attr" dest="text"/>-->
   <copyField source="shop_brands" dest="text"/>
   <copyField source="shop" dest="text"/>
   <copyField source="*_brand" dest="text"/>

   <!-- <copyField source="country" dest="suggestion"/>
   <copyField source="province" dest="suggestion"/>
   <copyField source="city" dest="suggestion"/>
   <copyField source="area" dest="suggestion"/>
   <copyField source="category_first" dest="suggestion"/>
   <copyField source="category_sencond" dest="suggestion"/>
   <copyField source="category_third" dest="suggestion"/>
   <copyField source="brand" dest="suggestion"/>
   <copyField source="brand_ch" dest="suggestion"/>
   <copyField source="brand_en" dest="suggestion"/>
   <copyField source="product_ch" dest="suggestion"/>
   <copyField source="product_en" dest="suggestion"/>
   <copyField source="*_attr" dest="suggestion"/> -->



 <!-- Field to use to determine and enforce document uniqueness. 
      Unless this field is marked with required="false", it will be a required field
   -->
 <uniqueKey>id</uniqueKey>

 <!-- DEPRECATED: The defaultSearchField is consulted by various query parsers when
  parsing a query string that isn't explicit about the field.  Machine (non-user)
  generated queries are best made explicit, or they can use the "df" request parameter
  which takes precedence over this.
  Note: Un-commenting defaultSearchField will be insufficient if your request handler
  in solrconfig.xml defines "df", which takes precedence. That would need to be removed.
 <defaultSearchField>text</defaultSearchField> -->

 <!-- DEPRECATED: The defaultOperator (AND|OR) is consulted by various query parsers
  when parsing a query string to determine if a clause of the query should be marked as
  required or optional, assuming the clause isn't already marked by some operator.
  The default is OR, which is generally assumed so it is not a good idea to change it
  globally here.  The "q.op" request parameter takes precedence over this.
 <solrQueryParser defaultOperator="OR"/> -->

  <!-- copyField commands copy one field to another at the time a document
        is added to the index.  It's used either to index the same field differently,
        or to add multiple fields to the same field for easier/faster searching.  -->

  
   <!-- Above, multiple source fields are copied to the [text] field. 
    Another way to map multiple source fields to the same 
    destination field is to use the dynamic field syntax. 
    copyField also supports a maxChars to copy setting.  -->
     
   <!-- <copyField source="*_t" dest="text" maxChars="3000"/> -->

   <!-- copy name to alphaNameSort, a field designed for sorting by name -->
   <!-- <copyField source="name" dest="alphaNameSort"/> -->
 
  
    <!-- field type definitions. The "name" attribute is
       just a label to be used by field definitions.  The "class"
       attribute and any other attributes determine the real
       behavior of the fieldType.
         Class names starting with "solr" refer to java classes in a
       standard package such as org.apache.solr.analysis
    -->

    <!-- The StrField type is not analyzed, but indexed/stored verbatim.
       It supports doc values but in that case the field needs to be
       single-valued and either required or have a default value.
      -->
    <fieldType name="string" class="solr.StrField" sortMissingLast="true" />

    <!-- boolean type: "true" or "false" -->
    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>

    <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
         currently supported on types that are sorted internally as strings
         and on numeric types.
       This includes "string","boolean", and, as of 3.5 (and 4.x),
       int, float, long, date, double, including the "Trie" variants.
       - If sortMissingLast="true", then a sort on this field will cause documents
         without the field to come after documents with the field,
         regardless of the requested sort order (asc or desc).
       - If sortMissingFirst="true", then a sort on this field will cause documents
         without the field to come before documents with the field,
         regardless of the requested sort order.
       - If sortMissingLast="false" and sortMissingFirst="false" (the default),
         then default lucene sorting will be used which places docs without the
         field first in an ascending sort and last in a descending sort.
    -->    

    <!--
      Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.

      These fields support doc values, but they require the field to be
      single-valued and either be required or have a default value.
    -->
    <fieldType name="int" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
    <fieldType name="float" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
    <fieldType name="long" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
    <fieldType name="double" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0"/>

    <!--
     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" docValues="true" precisionStep="8" positionIncrementGap="0"/>
    <fieldType name="tfloat" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
    <fieldType name="tlong" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
    <fieldType name="tdouble" class="solr.TrieDoubleField" docValues="true" precisionStep="8" 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 TrieDateField javadocs for more information.

         Note: For faster range queries, consider the tdate type
      -->
    <fieldType name="date" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0"/>

    <!-- A Trie based date field for faster date range queries and date faceting. -->
    <fieldType name="tdate" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0"/>


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

    <!-- The "RandomSortField" is not used to store or search any
         data.  You can declare fields of this type it in your schema
         to generate pseudo-random orderings of your docs for sorting 
         or function purposes.  The ordering is generated based on the field
         name and the version of the index. As long as the index version
         remains unchanged, and the same field name is reused,
         the ordering of the docs will be consistent.  
         If you want different psuedo-random orderings of documents,
         for the same version of the index, use a dynamicField and
         change the field name in the request.
     -->
    <fieldType name="random" class="solr.RandomSortField" indexed="true" />

    <!-- 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 text type for English text where stopwords and synonyms are managed using the REST API -->
    <fieldType name="managed_en" class="solr.TextField" positionIncrementGap="100">
      <analyzer>
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.ManagedStopFilterFactory" managed="english" />
        <filter class="solr.ManagedSynonymFilterFactory" managed="english" />
      </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" />
        <!-- 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" />
        <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"/>
        <!-- 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.
        -->
        <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"/>
  <!-- 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"
                />
        <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.
        -->
        <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"/>
        <!-- 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" />
        <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://docs.oracle.com/javase/8/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>

    <!-- 
      Example of using PathHierarchyTokenizerFactory at index time, so
      queries for paths match documents at that path, or in descendent paths
    -->
    <fieldType name="descendent_path" class="solr.TextField">
      <analyzer type="index">
  <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
      </analyzer>
      <analyzer type="query">
  <tokenizer class="solr.KeywordTokenizerFactory" />
      </analyzer>
    </fieldType>
    <!-- 
      Example of using PathHierarchyTokenizerFactory at query time, so
      queries for paths match documents at that path, or in ancestor paths
    -->
    <fieldType name="ancestor_path" class="solr.TextField">
      <analyzer type="index">
  <tokenizer class="solr.KeywordTokenizerFactory" />
      </analyzer>
      <analyzer type="query">
  <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
      </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"/>

    <!-- 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="0.001" distanceUnits="kilometers" />

    <!-- Spatial rectangle (bounding box) field. It supports most spatial predicates, and has
     special relevancy modes: score=overlapRatio|area|area2D (local-param to the query).  DocValues is recommended for
     relevancy. -->
    <fieldType name="bbox" class="solr.BBoxField"
               geo="true" distanceUnits="kilometers" numberType="_bbox_coord" />
    <fieldType name="_bbox_coord" class="solr.TrieDoubleField" precisionStep="8" docValues="true" useDocValuesAsStored="false" stored="false" />

   <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
        Parameters:
          defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
          precisionStep:   Specifies the precisionStep for the TrieLong field used for the amount
          providerClass:   Lets you plug in other exchange provider backend:
                           solr.FileExchangeRateProvider is the default and takes one parameter:
                             currencyConfig: name of an xml file holding exchange rates
                           solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
                             ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
                             refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
   -->
    <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
             


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

    <!-- Arabic -->
    <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <!-- for any non-arabic -->
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
        <!-- normalizes ? to ?, etc -->
        <filter class="solr.ArabicNormalizationFilterFactory"/>
        <filter class="solr.ArabicStemFilterFactory"/>
      </analyzer>
    </fieldType>

    <!-- Bulgarian -->
    <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/> 
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" /> 
        <filter class="solr.BulgarianStemFilterFactory"/>       
      </analyzer>
    </fieldType>
    
    <!-- Catalan -->
    <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <!-- removes l', etc -->
        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" />
        <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>       
      </analyzer>
    </fieldType>
    
    <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
    <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
      <analyzer>
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <!-- normalize width before bigram, as e.g. half-width dakuten combine  -->
        <filter class="solr.CJKWidthFilterFactory"/>
        <!-- for any non-CJK -->
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.CJKBigramFilterFactory"/>
      </analyzer>
    </fieldType>

    <!-- Kurdish -->
    <fieldType name="text_ckb" class="solr.TextField" positionIncrementGap="100">
      <analyzer>
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.SoraniNormalizationFilterFactory"/>
        <!-- for any latin text -->
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ckb.txt"/>
        <filter class="solr.SoraniStemFilterFactory"/>
      </analyzer>
    </fieldType>

    <!-- Czech -->
    <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" />
        <filter class="solr.CzechStemFilterFactory"/>       
      </analyzer>
    </fieldType>
    
    <!-- Danish -->
    <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
        <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>       
      </analyzer>
    </fieldType>
    
    <!-- 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" />
        <filter class="solr.GermanNormalizationFilterFactory"/>
        <filter class="solr.GermanLightStemFilterFactory"/>
        <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
      </analyzer>
    </fieldType>
    
    <!-- Greek -->
    <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <!-- greek specific lowercase for sigma -->
        <filter class="solr.GreekLowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
        <filter class="solr.GreekStemFilterFactory"/>
      </analyzer>
    </fieldType>
    
    <!-- Spanish -->
    <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
        <filter class="solr.SpanishLightStemFilterFactory"/>
        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
      </analyzer>
    </fieldType>
    
    <!-- Basque -->
    <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" />
        <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
      </analyzer>
    </fieldType>
    
    <!-- Persian -->
    <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
      <analyzer>
        <!-- for ZWNJ -->
        <charFilter class="solr.PersianCharFilterFactory"/>
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.ArabicNormalizationFilterFactory"/>
        <filter class="solr.PersianNormalizationFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" />
      </analyzer>
    </fieldType>
    
    <!-- Finnish -->
    <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
        <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
        <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
      </analyzer>
    </fieldType>
    
    <!-- French -->
    <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <!-- removes l', etc -->
        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
        <filter class="solr.FrenchLightStemFilterFactory"/>
        <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
      </analyzer>
    </fieldType>
    
    <!-- Irish -->
    <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <!-- removes d', etc -->
        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
        <!-- removes n-, etc. position increments is intentionally false! -->
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
        <filter class="solr.IrishLowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/>
        <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
      </analyzer>
    </fieldType>
    
    <!-- Galician -->
    <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" />
        <filter class="solr.GalicianStemFilterFactory"/>
        <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
      </analyzer>
    </fieldType>
    
    <!-- Hindi -->
    <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <!-- normalizes unicode representation -->
        <filter class="solr.IndicNormalizationFilterFactory"/>
        <!-- normalizes variation in spelling -->
        <filter class="solr.HindiNormalizationFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
        <filter class="solr.HindiStemFilterFactory"/>
      </analyzer>
    </fieldType>
    
    <!-- Hungarian -->
    <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
        <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
        <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->   
      </analyzer>
    </fieldType>
    
    <!-- Armenian -->
    <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" />
        <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
      </analyzer>
    </fieldType>
    
    <!-- Indonesian -->
    <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" />
        <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
        <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
      </analyzer>
    </fieldType>
    
    <!-- Italian -->
    <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <!-- removes l', etc -->
        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
        <filter class="solr.ItalianLightStemFilterFactory"/>
        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
      </analyzer>
    </fieldType>
    
    <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)

         NOTE: If you want to optimize search for precision, use default operator AND in your query
         parser config with <solrQueryParser defaultOperator="AND"/> further down in this file.  Use 
         OR if you would like to optimize for recall (default).
    -->
    <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
      <analyzer>
      <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)

           Kuromoji has a search mode (default) that does segmentation useful for search.  A heuristic
           is used to segment compounds into its parts and the compound itself is kept as synonym.

           Valid values for attribute mode are:
              normal: regular segmentation
              search: segmentation useful for search with synonyms compounds (default)
            extended: same as search mode, but unigrams unknown words (experimental)

           For some applications it might be good to use search mode for indexing and normal mode for
           queries to reduce recall and prevent parts of compounds from being matched and highlighted.
           Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.

           Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
           model with your own entries for segmentation, part-of-speech tags and readings without a need
           to specify weights.  Notice that user dictionaries have not been subject to extensive testing.

           User dictionary attributes are:
                     userDictionary: user dictionary filename
             userDictionaryEncoding: user dictionary encoding (default is UTF-8)

           See lang/userdict_ja.txt for a sample user dictionary file.

           Punctuation characters are discarded by default.  Use discardPunctuation="false" to keep them.

           See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
        -->
        <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
        <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
        <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
        <filter class="solr.JapaneseBaseFormFilterFactory"/>
        <!-- Removes tokens with certain part-of-speech tags -->
        <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
        <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
        <filter class="solr.CJKWidthFilterFactory"/>
        <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" />
        <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
        <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
        <!-- Lower-cases romaji characters -->
        <filter class="solr.LowerCaseFilterFactory"/>
      </analyzer>
    </fieldType>
    
    <!-- Latvian -->
    <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" />
        <filter class="solr.LatvianStemFilterFactory"/>
      </analyzer>
    </fieldType>
    
    <!-- Dutch -->
    <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
        <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
        <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
      </analyzer>
    </fieldType>
    
    <!-- Norwegian -->
    <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
        <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
        <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory" variant="nb"/> -->
        <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory" variant="nb"/> -->
        <!-- The "light" and "minimal" stemmers support variants: nb=Bokm?l, nn=Nynorsk, no=Both -->
      </analyzer>
    </fieldType>
    
    <!-- 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>
    
    <!-- Romanian -->
    <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" />
        <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
      </analyzer>
    </fieldType>
    
    <!-- Russian -->
    <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
        <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
        <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
      </analyzer>
    </fieldType>
    
    <!-- Swedish -->
    <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
        <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
        <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
      </analyzer>
    </fieldType>
    
    <!-- Thai -->
    <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.ThaiTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" />
      </analyzer>
    </fieldType>
    
    <!-- Turkish -->
    <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.ApostropheFilterFactory"/>
        <filter class="solr.TurkishLowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
        <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
      </analyzer>
    </fieldType>

    <!-- Pre-analyzed field type, allows inserting arbitrary token streams and stored values. -->
    <fieldType name="preanalyzed" class="solr.PreAnalyzedField">
      <!-- PreAnalyzedField's builtin index analyzer just decodes the pre-analyzed token stream. -->
      <analyzer type="query">
        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
      </analyzer>
    </fieldType>

  <!-- Similarity is the scoring routine for each document vs. a query.
       A custom Similarity or SimilarityFactory may be specified here, but 
       the default is fine for most applications.  
       For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
    -->
  <!--
     <similarity class="com.example.solr.CustomSimilarityFactory">
       <str name="paramkey">param value</str>
     </similarity>
    -->
    
    <fieldType name="text_ik" class="solr.TextField">
         <!-- 创建索引分词 -->
        <analyzer type="index">
                 <!-- IKTokenizerFactory 自定义工厂类 目的：使用useSmart 做细粒度或者粗粒度分词 true:粗粒度 false：细粒度 -->
                <tokenizer class="org.apache.lucene.analysis.ik.IKTokenizerFactory" useSmart="false"/>
           <filter class="solr.LowerCaseFilterFactory"/>
        </analyzer>
        <!-- 查询分词 -->
        <analyzer type="query">
           <tokenizer class="org.apache.lucene.analysis.ik.IKTokenizerFactory" useSmart="true"/>
           <!-- 同义词过滤器 -->
           <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
           <filter class="solr.LowerCaseFilterFactory"/>
        </analyzer>
    </fieldType>
    
   <fieldType name="text_spell" class="solr.TextField" positionIncrementGap="100">
         <!-- 推荐词分词索引-->
        <analyzer type="index">
            <tokenizer class="solr.WhitespaceTokenizerFactory"/>
            <filter class="solr.LowerCaseFilterFactory"/>
            <!-- 停用词过滤器 -->
            <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" format="snowball" />
            <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
        </analyzer>
        <!-- 推荐词分词查询-->
        <analyzer type="query">
            <tokenizer class="solr.WhitespaceTokenizerFactory"/>
            <filter class="solr.LowerCaseFilterFactory"/>
            <!-- 过滤 停用词 和同义词 -->
            <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" format="snowball" />
            <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
        </analyzer>
    </fieldType>  

   
</schema>

2.商品schema.xml

<?xml version="1.0" encoding="UTF-8" ?>
<schema name="gomecar" version="1.6">
   <field name="_version_" type="long" indexed="true" stored="false" />  
   <field name="_root_" type="string" indexed="true" stored="false" docValues="false" />

   <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" /> 
   <!-- 国家id  -->
   <field name="country_id" type="string" indexed="true" stored="true" required="false" multiValued="false" />
   <!--string不进行分词 -->
   <!--国家名 -->
   <field name="country" type="string" indexed="true" stored="true" required="false" multiValued="false" />
   <!--string不进行分词 -->
   <!-- 省份id ======== -->
   <field name="province_id" type="string" indexed="true" stored="true" required="false" multiValued="false" />
   <!-- 省份名 -->
   <field name="province" type="string" indexed="true" stored="true" required="false" multiValued="false" />
   <!-- 城市id -->
   <field name="city_id" type="string" indexed="true" stored="true" required="false" multiValued="false" />
    <!-- 市名 -->
   <field name="city" type="string" indexed="true" stored="true" required="false" multiValued="false" />
    <!-- 区域id -->
   <field name="area_id" type="string" indexed="true" stored="true" required="false" multiValued="false" />
   <!-- 区域-->
   <field name="area" type="string" indexed="true" stored="true" required="false" multiValued="false" />
    <!-- 店铺id -->
   <field name="shop_id" type="string" indexed="true" stored="true" required="false" multiValued="false" />
   <!-- 店铺 -->
   <field name="shop" type="string" indexed="true" stored="true" required="false" multiValued="false" />
    <!-- 店铺经纬度 -->
   <field name="shop_location" type="location_rpt" indexed="true" stored="true" required="false" multiValued="false" omitNorms="true" />
   <!-- 店铺所在地 -->
   <field name="shop_coordinate" type="string" indexed="true" stored="true" required="false" multiValued="false" />
   <!-- 店铺星级 -->
   <field name="shop_level" type="string" indexed="true" stored="true" required="false" multiValued="false" />
   <!-- 店铺的品牌ID -->
   <field name="shop_brand_id" type="string" indexed="true" stored="true" required="false" multiValued="true" />
    <!-- 店铺的品牌 -->
   <field name="shop_brands" type="string" indexed="true" stored="true" required="false" multiValued="true" />
   <!-- 一级分类id  -->
   <field name="category_first_id" type="string" indexed="true" stored="true" required="false" multiValued="false" />
   <!-- 一级分类名 -->
   <field name="category_first" type="string" indexed="true" stored="true" required="false" multiValued="false" />
   <!-- 二级分类id -->
   <field name="category_second_id" type="string" indexed="true" stored="true" required="false" multiValued="false" />
   <!-- 二级分类名 -->
   <field name="category_second" type="string" indexed="true" stored="true" required="false" multiValued="false" />
   <!-- 三级分类id -->
   <field name="category_third_id" type="string" indexed="true" stored="true" required="false" multiValued="false" />
   <!-- 三级分类名 -->
   <field name="category_third" type="string" indexed="true" stored="true" required="false" multiValued="false" />
   
   
    <!-- 多个分类 -->
   <field name="cats" type="string" indexed="true" stored="true" required="false" multiValued="true" />
   
   <!-- 品牌id -->
   <field name="brand_id" type="string" indexed="true" stored="true" required="false" multiValued="false" />
   <!-- 品牌名 -->
   <field name="brand" type="string" indexed="true" stored="true" required="false" multiValued="false" />
   <!-- 品牌英文名 -->
   <field name="brand_en" type="string" indexed="true" stored="true" required="false" multiValued="false" />
   <!--  品牌中文名 -->
   <field name="brand_ch" type="text_ik" indexed="true" stored="false" required="false" multiValued="false" />
   <!-- 属性名 -->
   <field name="attr_name" type="string" indexed="true" stored="true" required="false" multiValued="true" />
   <!--  sku -->
   <field name="sku" type="string" indexed="true" stored="true" required="true" multiValued="false" /> 
   <!-- spu -->
   <field name="spu" type="string" indexed="true" stored="true" required="true" multiValued="false" />
    <!-- spu -->
   <field name="gome_sku" type="string" indexed="true" stored="true" required="true" multiValued="false" /> 
    <!--  商品名 -->
   <field name="product_ch" type="text_ik" indexed="true" stored="true" required="true" multiValued="false" />
   <!-- 广告 -->
   <field name="adver" type="string" indexed="false" stored="true" required="false" multiValued="false" />
    <!-- 商品拼音名 -->
   <field name="product_pinyin" type="string" indexed="true" stored="true" required="false" multiValued="false" />
   <!-- 商品中文简称 -->
   <field name="product_short_ch" type="text_ik" indexed="true" stored="false" required="false" multiValued="false" />
   <!-- 商品英文名 -->
   <field name="product_en" type="text_ik" indexed="true" stored="false" required="false" multiValued="false" />
   <!-- 商品图片地址 -->
   <field name="product_img" type="string" indexed="false" stored="true" required="false" multiValued="false" />
   <!-- <field name="product_href" type="string" indexed="false" stored="true" required="false" multiValued="false" /> -->
   <!-- 商品原价 -->
   <field name="product_proto_price" type="float" indexed="false" stored="true" required="false" multiValued="false" />
   <!-- 商品售价 -->
   <field name="product_sale_price" type="float" indexed="true" stored="true" required="true" multiValued="false" />
    <!-- 商品vip售价 -->
   <field name="product_vip_price" type="float" indexed="true" stored="true" required="true" multiValued="false" />
    <!--  是否整车 -->
   <field name="is_car" type="boolean" indexed="true" stored="true" required="false" multiValued="false" />
   <!--  是否自营 -->
   <field name="is_self" type="boolean" indexed="true" stored="true" required="true" multiValued="false" />
   <!--  售卖类型-->
   <field name="sale_type" type="string" indexed="true" stored="true" required="true" multiValued="false" />
   <!-- 是否上架 -->
   <field name="is_shelves" type="boolean" indexed="true" stored="true" required="true" multiValued="false" />
   <!-- 好评率 -->
   <field name="good_comment_rate" type="int" indexed="true" stored="true" required="true" multiValued="false" />
   <!-- 好评数 -->
   <field name="good_comment_num" type="int" indexed="true" stored="true" required="true" multiValued="false" />
   <!--  是否有货-->
   <field name="is_in_store" type="boolean" indexed="true" stored="true" required="true" multiValued="false" />
   <!-- 售卖数量 -->
   <field name="sale_num" type="int" indexed="true" stored="true" required="true" multiValued="false" />
   <!-- 关注度 -->
   <field name="attention" type="string" indexed="true" stored="true" required="true" multiValued="false" />
   <!--  创建时间 -->
   <field name="create_time" type="date" indexed="false" stored="false" required="false" multiValued="false" />
    <!--  上架时间 -->
   <field name="shelves_time" type="date" indexed="true" stored="false" required="false" multiValued="false" />
   <!-- 过期时间 -->
   <field name="valid_time" type="date" indexed="false" stored="false" required="false" multiValued="false" />
   <!--  最后更新时间 -->
   <field name="last_modified" type="date" indexed="true" stored="false" required="false" multiValued="false" />
   
   
   <!-- 默认搜索域 将所有文本域放入里面。必须让mutiValued为true  多值-->
   <field name="text" type="text_ik" indexed="true" stored="false" multiValued="true"/>
   <field name="suggestion" type="text_spell" indexed="true" stored="true" multiValued="true"/>
 
   <!-- Dynamic field definitions allow using convention over configuration
       for fields via the specification of patterns to match field names. 
       EXAMPLE:  name="*_i" will match any field ending in _i (like myid_i, z_i)
       RESTRICTION: the glob-like pattern in the name attribute must have
       a "*" only at the start or the end.  -->
    <!-- 所有_id的域走此动态域，方便动态增加-->
   <dynamicField name="*_id"  type="int"    indexed="true"  stored="true"/>
   <!-- 所有_ch的域都使用ik进行分词-->
   <dynamicField name="*_ch"  type="text_ik"    indexed="true"  stored="true"/>
   <dynamicField name="*_i"  type="int"    indexed="true"  stored="true"/>
   <dynamicField name="*_is" type="int"    indexed="true"  stored="true"  multiValued="true"/>
   <dynamicField name="*_s"  type="string"  indexed="true"  stored="true" />
   <dynamicField name="*_ss" type="string"  indexed="true"  stored="true" multiValued="true"/>
   <dynamicField name="*_l"  type="long"   indexed="true"  stored="true"/>
   <dynamicField name="*_ls" type="long"   indexed="true"  stored="true"  multiValued="true"/>
   <dynamicField name="*_t"  type="text_general"    indexed="true"  stored="true"/>
   <dynamicField name="*_txt" type="text_general"   indexed="true"  stored="true" multiValued="true"/>
   <dynamicField name="*_en" type="text_en"    indexed="true"  stored="true" multiValued="true"/>
   <dynamicField name="*_b"  type="boolean" indexed="true" stored="true"/>
   <dynamicField name="*_bs" type="boolean" indexed="true" stored="true"  multiValued="true"/>
   <dynamicField name="*_f"  type="float"  indexed="true"  stored="true"/>
   <dynamicField name="*_fs" type="float"  indexed="true"  stored="true"  multiValued="true"/>
   <dynamicField name="*_d"  type="double" indexed="true"  stored="true"/>
   <dynamicField name="*_ds" type="double" indexed="true"  stored="true"  multiValued="true"/>

   <!-- Type used to index the lat and lon components for the "location" FieldType -->
   <dynamicField name="*_coordinate"  type="tdouble" indexed="true"  stored="false" useDocValuesAsStored="false" />

   <dynamicField name="*_dt"  type="date"    indexed="true"  stored="true"/>
   <dynamicField name="*_dts" type="date"    indexed="true"  stored="true" multiValued="true"/>
   <dynamicField name="*_p"  type="location" indexed="true" stored="true"/>

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

   <dynamicField name="*_c"   type="currency" indexed="true"  stored="true"/>

   <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
   <!--商品属性拓展字段-->
   <dynamicField name="*_attr" type="string" indexed="true" stored="true" multiValued="true"/>
  <dynamicField name="*_attr_c" type="text_ik" indexed="true" stored="false" multiValued="true"/>

   <dynamicField name="random_*" type="random" />
  


   <!-- 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" /-->
     
   <copyField source="country" dest="text"/>
   <copyField source="province" dest="text"/>
   <copyField source="city" dest="text"/>
   <copyField source="area" dest="text"/>
   <copyField source="category_first" dest="text"/>
   <copyField source="category_second" dest="text"/>
   <copyField source="category_third" dest="text"/>
   <copyField source="brand" dest="text"/> 
   <copyField source="brand_ch" dest="text"/>
   <copyField source="brand_en" dest="text"/>
   <copyField source="product_ch" dest="text"/>
   <copyField source="product_en" dest="text"/>
   <copyField source="shop" dest="text"/>
   <copyField source="*_attr" dest="text"/>
   <copyField source="shop_brands" dest="text"/>

   <!-- <copyField source="country" dest="suggestion"/>
   <copyField source="province" dest="suggestion"/>
   <copyField source="city" dest="suggestion"/>
   <copyField source="area" dest="suggestion"/>
   <copyField source="category_first" dest="suggestion"/>
   <copyField source="category_sencond" dest="suggestion"/>
   <copyField source="category_third" dest="suggestion"/>
   <copyField source="brand" dest="suggestion"/>
   <copyField source="brand_ch" dest="suggestion"/>
   <copyField source="brand_en" dest="suggestion"/>
   <copyField source="product_ch" dest="suggestion"/>
   <copyField source="product_en" dest="suggestion"/>
   <copyField source="*_attr" dest="suggestion"/> -->



 <!-- Field to use to determine and enforce document uniqueness. 
      Unless this field is marked with required="false", it will be a required field
   -->
 <uniqueKey>id</uniqueKey>

 <!-- DEPRECATED: The defaultSearchField is consulted by various query parsers when
  parsing a query string that isn't explicit about the field.  Machine (non-user)
  generated queries are best made explicit, or they can use the "df" request parameter
  which takes precedence over this.
  Note: Un-commenting defaultSearchField will be insufficient if your request handler
  in solrconfig.xml defines "df", which takes precedence. That would need to be removed.
 <defaultSearchField>text</defaultSearchField> -->

 <!-- DEPRECATED: The defaultOperator (AND|OR) is consulted by various query parsers
  when parsing a query string to determine if a clause of the query should be marked as
  required or optional, assuming the clause isn't already marked by some operator.
  The default is OR, which is generally assumed so it is not a good idea to change it
  globally here.  The "q.op" request parameter takes precedence over this.
 <solrQueryParser defaultOperator="OR"/> -->

  <!-- copyField commands copy one field to another at the time a document
        is added to the index.  It's used either to index the same field differently,
        or to add multiple fields to the same field for easier/faster searching.  -->

  
   <!-- Above, multiple source fields are copied to the [text] field. 
    Another way to map multiple source fields to the same 
    destination field is to use the dynamic field syntax. 
    copyField also supports a maxChars to copy setting.  -->
     
   <!-- <copyField source="*_t" dest="text" maxChars="3000"/> -->

   <!-- copy name to alphaNameSort, a field designed for sorting by name -->
   <!-- <copyField source="name" dest="alphaNameSort"/> -->
 
  
    <!-- field type definitions. The "name" attribute is
       just a label to be used by field definitions.  The "class"
       attribute and any other attributes determine the real
       behavior of the fieldType.
         Class names starting with "solr" refer to java classes in a
       standard package such as org.apache.solr.analysis
    -->

    <!-- The StrField type is not analyzed, but indexed/stored verbatim.
       It supports doc values but in that case the field needs to be
       single-valued and either required or have a default value.
      -->
    <fieldType name="string" class="solr.StrField" sortMissingLast="true" />

    <!-- boolean type: "true" or "false" -->
    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>

    <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
         currently supported on types that are sorted internally as strings
         and on numeric types.
       This includes "string","boolean", and, as of 3.5 (and 4.x),
       int, float, long, date, double, including the "Trie" variants.
       - If sortMissingLast="true", then a sort on this field will cause documents
         without the field to come after documents with the field,
         regardless of the requested sort order (asc or desc).
       - If sortMissingFirst="true", then a sort on this field will cause documents
         without the field to come before documents with the field,
         regardless of the requested sort order.
       - If sortMissingLast="false" and sortMissingFirst="false" (the default),
         then default lucene sorting will be used which places docs without the
         field first in an ascending sort and last in a descending sort.
    -->    

    <!--
      Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.

      These fields support doc values, but they require the field to be
      single-valued and either be required or have a default value.
    -->
    <fieldType name="int" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
    <fieldType name="float" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
    <fieldType name="long" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
    <fieldType name="double" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0"/>

    <!--
     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" docValues="true" precisionStep="8" positionIncrementGap="0"/>
    <fieldType name="tfloat" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
    <fieldType name="tlong" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
    <fieldType name="tdouble" class="solr.TrieDoubleField" docValues="true" precisionStep="8" 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 TrieDateField javadocs for more information.

         Note: For faster range queries, consider the tdate type
      -->
    <fieldType name="date" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0"/>

    <!-- A Trie based date field for faster date range queries and date faceting. -->
    <fieldType name="tdate" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0"/>


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

    <!-- The "RandomSortField" is not used to store or search any
         data.  You can declare fields of this type it in your schema
         to generate pseudo-random orderings of your docs for sorting 
         or function purposes.  The ordering is generated based on the field
         name and the version of the index. As long as the index version
         remains unchanged, and the same field name is reused,
         the ordering of the docs will be consistent.  
         If you want different psuedo-random orderings of documents,
         for the same version of the index, use a dynamicField and
         change the field name in the request.
     -->
    <fieldType name="random" class="solr.RandomSortField" indexed="true" />

    <!-- 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 text type for English text where stopwords and synonyms are managed using the REST API -->
    <fieldType name="managed_en" class="solr.TextField" positionIncrementGap="100">
      <analyzer>
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.ManagedStopFilterFactory" managed="english" />
        <filter class="solr.ManagedSynonymFilterFactory" managed="english" />
      </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" />
        <!-- 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" />
        <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"/>
        <!-- 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.
        -->
        <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"/>
  <!-- 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"
                />
        <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.
        -->
        <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"/>
        <!-- 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" />
        <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://docs.oracle.com/javase/8/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>

    <!-- 
      Example of using PathHierarchyTokenizerFactory at index time, so
      queries for paths match documents at that path, or in descendent paths
    -->
    <fieldType name="descendent_path" class="solr.TextField">
      <analyzer type="index">
  <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
      </analyzer>
      <analyzer type="query">
  <tokenizer class="solr.KeywordTokenizerFactory" />
      </analyzer>
    </fieldType>
    <!-- 
      Example of using PathHierarchyTokenizerFactory at query time, so
      queries for paths match documents at that path, or in ancestor paths
    -->
    <fieldType name="ancestor_path" class="solr.TextField">
      <analyzer type="index">
  <tokenizer class="solr.KeywordTokenizerFactory" />
      </analyzer>
      <analyzer type="query">
  <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
      </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"/>

    <!-- 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="0.001" distanceUnits="kilometers" />

    <!-- Spatial rectangle (bounding box) field. It supports most spatial predicates, and has
     special relevancy modes: score=overlapRatio|area|area2D (local-param to the query).  DocValues is recommended for
     relevancy. -->
    <fieldType name="bbox" class="solr.BBoxField"
               geo="true" distanceUnits="kilometers" numberType="_bbox_coord" />
    <fieldType name="_bbox_coord" class="solr.TrieDoubleField" precisionStep="8" docValues="true" useDocValuesAsStored="false" stored="false" />

   <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
        Parameters:
          defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
          precisionStep:   Specifies the precisionStep for the TrieLong field used for the amount
          providerClass:   Lets you plug in other exchange provider backend:
                           solr.FileExchangeRateProvider is the default and takes one parameter:
                             currencyConfig: name of an xml file holding exchange rates
                           solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
                             ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
                             refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
   -->
    <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
             


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

    <!-- Arabic -->
    <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <!-- for any non-arabic -->
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
        <!-- normalizes ? to ?, etc -->
        <filter class="solr.ArabicNormalizationFilterFactory"/>
        <filter class="solr.ArabicStemFilterFactory"/>
      </analyzer>
    </fieldType>

    <!-- Bulgarian -->
    <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/> 
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" /> 
        <filter class="solr.BulgarianStemFilterFactory"/>       
      </analyzer>
    </fieldType>
    
    <!-- Catalan -->
    <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <!-- removes l', etc -->
        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" />
        <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>       
      </analyzer>
    </fieldType>
    
    <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
    <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
      <analyzer>
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <!-- normalize width before bigram, as e.g. half-width dakuten combine  -->
        <filter class="solr.CJKWidthFilterFactory"/>
        <!-- for any non-CJK -->
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.CJKBigramFilterFactory"/>
      </analyzer>
    </fieldType>

    <!-- Kurdish -->
    <fieldType name="text_ckb" class="solr.TextField" positionIncrementGap="100">
      <analyzer>
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.SoraniNormalizationFilterFactory"/>
        <!-- for any latin text -->
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ckb.txt"/>
        <filter class="solr.SoraniStemFilterFactory"/>
      </analyzer>
    </fieldType>

    <!-- Czech -->
    <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" />
        <filter class="solr.CzechStemFilterFactory"/>       
      </analyzer>
    </fieldType>
    
    <!-- Danish -->
    <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
        <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>       
      </analyzer>
    </fieldType>
    
    <!-- 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" />
        <filter class="solr.GermanNormalizationFilterFactory"/>
        <filter class="solr.GermanLightStemFilterFactory"/>
        <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
      </analyzer>
    </fieldType>
    
    <!-- Greek -->
    <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <!-- greek specific lowercase for sigma -->
        <filter class="solr.GreekLowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
        <filter class="solr.GreekStemFilterFactory"/>
      </analyzer>
    </fieldType>
    
    <!-- Spanish -->
    <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
        <filter class="solr.SpanishLightStemFilterFactory"/>
        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
      </analyzer>
    </fieldType>
    
    <!-- Basque -->
    <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" />
        <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
      </analyzer>
    </fieldType>
    
    <!-- Persian -->
    <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
      <analyzer>
        <!-- for ZWNJ -->
        <charFilter class="solr.PersianCharFilterFactory"/>
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.ArabicNormalizationFilterFactory"/>
        <filter class="solr.PersianNormalizationFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" />
      </analyzer>
    </fieldType>
    
    <!-- Finnish -->
    <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
        <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
        <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
      </analyzer>
    </fieldType>
    
    <!-- French -->
    <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <!-- removes l', etc -->
        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
        <filter class="solr.FrenchLightStemFilterFactory"/>
        <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
      </analyzer>
    </fieldType>
    
    <!-- Irish -->
    <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <!-- removes d', etc -->
        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
        <!-- removes n-, etc. position increments is intentionally false! -->
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
        <filter class="solr.IrishLowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/>
        <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
      </analyzer>
    </fieldType>
    
    <!-- Galician -->
    <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" />
        <filter class="solr.GalicianStemFilterFactory"/>
        <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
      </analyzer>
    </fieldType>
    
    <!-- Hindi -->
    <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <!-- normalizes unicode representation -->
        <filter class="solr.IndicNormalizationFilterFactory"/>
        <!-- normalizes variation in spelling -->
        <filter class="solr.HindiNormalizationFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
        <filter class="solr.HindiStemFilterFactory"/>
      </analyzer>
    </fieldType>
    
    <!-- Hungarian -->
    <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
        <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
        <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->   
      </analyzer>
    </fieldType>
    
    <!-- Armenian -->
    <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" />
        <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
      </analyzer>
    </fieldType>
    
    <!-- Indonesian -->
    <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" />
        <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
        <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
      </analyzer>
    </fieldType>
    
    <!-- Italian -->
    <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <!-- removes l', etc -->
        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
        <filter class="solr.ItalianLightStemFilterFactory"/>
        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
      </analyzer>
    </fieldType>
    
    <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)

         NOTE: If you want to optimize search for precision, use default operator AND in your query
         parser config with <solrQueryParser defaultOperator="AND"/> further down in this file.  Use 
         OR if you would like to optimize for recall (default).
    -->
    <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
      <analyzer>
      <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)

           Kuromoji has a search mode (default) that does segmentation useful for search.  A heuristic
           is used to segment compounds into its parts and the compound itself is kept as synonym.

           Valid values for attribute mode are:
              normal: regular segmentation
              search: segmentation useful for search with synonyms compounds (default)
            extended: same as search mode, but unigrams unknown words (experimental)

           For some applications it might be good to use search mode for indexing and normal mode for
           queries to reduce recall and prevent parts of compounds from being matched and highlighted.
           Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.

           Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
           model with your own entries for segmentation, part-of-speech tags and readings without a need
           to specify weights.  Notice that user dictionaries have not been subject to extensive testing.

           User dictionary attributes are:
                     userDictionary: user dictionary filename
             userDictionaryEncoding: user dictionary encoding (default is UTF-8)

           See lang/userdict_ja.txt for a sample user dictionary file.

           Punctuation characters are discarded by default.  Use discardPunctuation="false" to keep them.

           See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
        -->
        <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
        <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
        <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
        <filter class="solr.JapaneseBaseFormFilterFactory"/>
        <!-- Removes tokens with certain part-of-speech tags -->
        <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
        <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
        <filter class="solr.CJKWidthFilterFactory"/>
        <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" />
        <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
        <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
        <!-- Lower-cases romaji characters -->
        <filter class="solr.LowerCaseFilterFactory"/>
      </analyzer>
    </fieldType>
    
    <!-- Latvian -->
    <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" />
        <filter class="solr.LatvianStemFilterFactory"/>
      </analyzer>
    </fieldType>
    
    <!-- Dutch -->
    <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
        <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
        <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
      </analyzer>
    </fieldType>
    
    <!-- Norwegian -->
    <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
        <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
        <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory" variant="nb"/> -->
        <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory" variant="nb"/> -->
        <!-- The "light" and "minimal" stemmers support variants: nb=Bokm?l, nn=Nynorsk, no=Both -->
      </analyzer>
    </fieldType>
    
    <!-- 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>
    
    <!-- Romanian -->
    <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" />
        <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
      </analyzer>
    </fieldType>
    
    <!-- Russian -->
    <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
        <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
        <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
      </analyzer>
    </fieldType>
    
    <!-- Swedish -->
    <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
        <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
        <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
      </analyzer>
    </fieldType>
    
    <!-- Thai -->
    <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.ThaiTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" />
      </analyzer>
    </fieldType>
    
    <!-- Turkish -->
    <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.ApostropheFilterFactory"/>
        <filter class="solr.TurkishLowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
        <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
      </analyzer>
    </fieldType>

    <!-- Pre-analyzed field type, allows inserting arbitrary token streams and stored values. -->
    <fieldType name="preanalyzed" class="solr.PreAnalyzedField">
      <!-- PreAnalyzedField's builtin index analyzer just decodes the pre-analyzed token stream. -->
      <analyzer type="query">
        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
      </analyzer>
    </fieldType>

  <!-- Similarity is the scoring routine for each document vs. a query.
       A custom Similarity or SimilarityFactory may be specified here, but 
       the default is fine for most applications.  
       For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
    -->
  <!--
     <similarity class="com.example.solr.CustomSimilarityFactory">
       <str name="paramkey">param value</str>
     </similarity>
    -->
    
    <fieldType name="text_ik" class="solr.TextField">
         <!-- 创建索引分词 -->
        <analyzer type="index">
                 <!-- IKTokenizerFactory 自定义工厂类 目的：使用useSmart 做细粒度或者粗粒度分词 true:粗粒度 false：细粒度 -->
                <tokenizer class="org.apache.lucene.analysis.ik.IKTokenizerFactory" useSmart="false"/>
           <filter class="solr.LowerCaseFilterFactory"/>
        </analyzer>
        <!-- 查询分词 -->
        <analyzer type="query">
           <tokenizer class="org.apache.lucene.analysis.ik.IKTokenizerFactory" useSmart="true"/>
           <!-- 同义词过滤器 -->
           <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
           <filter class="solr.LowerCaseFilterFactory"/>
        </analyzer>
    </fieldType>
    
   <fieldType name="text_spell" class="solr.TextField" positionIncrementGap="100">
         <!-- 推荐词分词索引-->
        <analyzer type="index">
            <tokenizer class="solr.WhitespaceTokenizerFactory"/>
            <filter class="solr.LowerCaseFilterFactory"/>
            <!-- 停用词过滤器 -->
            <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" format="snowball" />
            <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
        </analyzer>
        <!-- 推荐词分词查询-->
        <analyzer type="query">
            <tokenizer class="solr.WhitespaceTokenizerFactory"/>
            <filter class="solr.LowerCaseFilterFactory"/>
            <!-- 过滤 停用词 和同义词 -->
            <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" format="snowball" />
            <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
        </analyzer>
    </fieldType>  

   
</schema>

3.拼音schema.xml

<?xml version="1.0" encoding="UTF-8" ?>
<schema name="higo_pinyin" version="1.6">
   <field name="_version_" type="long" indexed="true" stored="false" />  
   <field name="_root_" type="string" indexed="true" stored="false" docValues="false" />

   <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" /> 
   <field name="name" type="text_pinyin" indexed="true" stored="true" required="false" multiValued="false" />
   <field name="pinyin" type="text_pinyin" indexed="true" stored="true" required="false" multiValued="false" />
   <field name="abbre" type="text_pinyin" indexed="true" stored="true" required="false" multiValued="false" />
   <field name="division_code" type="string" indexed="true" stored="true" required="false" multiValued="false" />
   <field name="first_spell" type="string" indexed="true" stored="true" required="false" multiValued="false" />
   <field name="point_num" type="float" indexed="true" stored="true" required="false" multiValued="false" />
   <field name="score_num" type="float" indexed="true" stored="true" required="false" multiValued="false" />
   <field name="type" type="string" indexed="true" stored="true" required="false" multiValued="false" />
   <field name="div_flg" type="string" indexed="true" stored="true" required="false" multiValued="false" />
   <field name="create_date" type="date" indexed="true" stored="true" required="false" multiValued="false" />
   <field name="modify_date" type="date" indexed="true" stored="true" required="false" multiValued="false" />
   
   <!-- 默认搜索域 将所有文本域放入里面。必须让mutiValued为true-->
   <field name="text" type="text_pinyin" indexed="true" stored="false" multiValued="true"/>
   
   <copyField source="name" dest="text"/>
   <copyField source="pinyin" dest="text"/>
   <copyField source="abbre" dest="text"/>
   <copyField source="first_spell" dest="text"/>
 
   <!-- Dynamic field definitions allow using convention over configuration
       for fields via the specification of patterns to match field names. 
       EXAMPLE:  name="*_i" will match any field ending in _i (like myid_i, z_i)
       RESTRICTION: the glob-like pattern in the name attribute must have
       a "*" only at the start or the end.  -->
    <!-- 所有_id的域走此动态域，方便动态增加-->
   <dynamicField name="*_id"  type="int"    indexed="true"  stored="true"/>
   <!-- 所有_ch的域都使用ik进行分词-->
   <dynamicField name="*_ch"  type="text_ik"    indexed="true"  stored="true"/>
   <dynamicField name="*_i"  type="int"    indexed="true"  stored="true"/>
   <dynamicField name="*_is" type="int"    indexed="true"  stored="true"  multiValued="true"/>
   <dynamicField name="*_s"  type="string"  indexed="true"  stored="true" />
   <dynamicField name="*_ss" type="string"  indexed="true"  stored="true" multiValued="true"/>
   <dynamicField name="*_l"  type="long"   indexed="true"  stored="true"/>
   <dynamicField name="*_ls" type="long"   indexed="true"  stored="true"  multiValued="true"/>
   <dynamicField name="*_t"  type="text_general"    indexed="true"  stored="true"/>
   <dynamicField name="*_txt" type="text_general"   indexed="true"  stored="true" multiValued="true"/>
   <dynamicField name="*_en" type="text_en"    indexed="true"  stored="true" multiValued="true"/>
   <dynamicField name="*_b"  type="boolean" indexed="true" stored="true"/>
   <dynamicField name="*_bs" type="boolean" indexed="true" stored="true"  multiValued="true"/>
   <dynamicField name="*_f"  type="float"  indexed="true"  stored="true"/>
   <dynamicField name="*_fs" type="float"  indexed="true"  stored="true"  multiValued="true"/>
   <dynamicField name="*_d"  type="double" indexed="true"  stored="true"/>
   <dynamicField name="*_ds" type="double" indexed="true"  stored="true"  multiValued="true"/>

   <!-- Type used to index the lat and lon components for the "location" FieldType -->
   <dynamicField name="*_coordinate"  type="tdouble" indexed="true"  stored="false" useDocValuesAsStored="false" />

   <dynamicField name="*_dt"  type="date"    indexed="true"  stored="true"/>
   <dynamicField name="*_dts" type="date"    indexed="true"  stored="true" multiValued="true"/>
   <dynamicField name="*_p"  type="location" indexed="true" stored="true"/>

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

   <dynamicField name="*_c"   type="currency" indexed="true"  stored="true"/>

   <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
   <dynamicField name="*_attr" type="string" indexed="true" stored="true" multiValued="true"/>
   <dynamicField name="*_attr_c" type="text_ik" indexed="true" stored="false" multiValued="true"/>
   <dynamicField name="random_*" type="random" />

   <!-- 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" /-->

 <!-- Field to use to determine and enforce document uniqueness. 
      Unless this field is marked with required="false", it will be a required field
   -->
 <uniqueKey>id</uniqueKey>

 <!-- DEPRECATED: The defaultSearchField is consulted by various query parsers when
  parsing a query string that isn't explicit about the field.  Machine (non-user)
  generated queries are best made explicit, or they can use the "df" request parameter
  which takes precedence over this.
  Note: Un-commenting defaultSearchField will be insufficient if your request handler
  in solrconfig.xml defines "df", which takes precedence. That would need to be removed.
 <defaultSearchField>text</defaultSearchField> -->

 <!-- DEPRECATED: The defaultOperator (AND|OR) is consulted by various query parsers
  when parsing a query string to determine if a clause of the query should be marked as
  required or optional, assuming the clause isn't already marked by some operator.
  The default is OR, which is generally assumed so it is not a good idea to change it
  globally here.  The "q.op" request parameter takes precedence over this.
 <solrQueryParser defaultOperator="OR"/> -->

  <!-- copyField commands copy one field to another at the time a document
        is added to the index.  It's used either to index the same field differently,
        or to add multiple fields to the same field for easier/faster searching.  -->

  
   <!-- Above, multiple source fields are copied to the [text] field. 
    Another way to map multiple source fields to the same 
    destination field is to use the dynamic field syntax. 
    copyField also supports a maxChars to copy setting.  -->
     
   <!-- <copyField source="*_t" dest="text" maxChars="3000"/> -->

   <!-- copy name to alphaNameSort, a field designed for sorting by name -->
   <!-- <copyField source="name" dest="alphaNameSort"/> -->
 
  
    <!-- field type definitions. The "name" attribute is
       just a label to be used by field definitions.  The "class"
       attribute and any other attributes determine the real
       behavior of the fieldType.
         Class names starting with "solr" refer to java classes in a
       standard package such as org.apache.solr.analysis
    -->

    <!-- The StrField type is not analyzed, but indexed/stored verbatim.
       It supports doc values but in that case the field needs to be
       single-valued and either required or have a default value.
      -->
    <fieldType name="string" class="solr.StrField" sortMissingLast="true" />

    <!-- boolean type: "true" or "false" -->
    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>

    <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
         currently supported on types that are sorted internally as strings
         and on numeric types.
       This includes "string","boolean", and, as of 3.5 (and 4.x),
       int, float, long, date, double, including the "Trie" variants.
       - If sortMissingLast="true", then a sort on this field will cause documents
         without the field to come after documents with the field,
         regardless of the requested sort order (asc or desc).
       - If sortMissingFirst="true", then a sort on this field will cause documents
         without the field to come before documents with the field,
         regardless of the requested sort order.
       - If sortMissingLast="false" and sortMissingFirst="false" (the default),
         then default lucene sorting will be used which places docs without the
         field first in an ascending sort and last in a descending sort.
    -->    

    <!--
      Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.

      These fields support doc values, but they require the field to be
      single-valued and either be required or have a default value.
    -->
    <fieldType name="int" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
    <fieldType name="float" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
    <fieldType name="long" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
    <fieldType name="double" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0"/>

    <!--
     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" docValues="true" precisionStep="8" positionIncrementGap="0"/>
    <fieldType name="tfloat" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
    <fieldType name="tlong" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
    <fieldType name="tdouble" class="solr.TrieDoubleField" docValues="true" precisionStep="8" 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 TrieDateField javadocs for more information.

         Note: For faster range queries, consider the tdate type
      -->
    <fieldType name="date" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0"/>

    <!-- A Trie based date field for faster date range queries and date faceting. -->
    <fieldType name="tdate" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0"/>


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

    <!-- The "RandomSortField" is not used to store or search any
         data.  You can declare fields of this type it in your schema
         to generate pseudo-random orderings of your docs for sorting 
         or function purposes.  The ordering is generated based on the field
         name and the version of the index. As long as the index version
         remains unchanged, and the same field name is reused,
         the ordering of the docs will be consistent.  
         If you want different psuedo-random orderings of documents,
         for the same version of the index, use a dynamicField and
         change the field name in the request.
     -->
    <fieldType name="random" class="solr.RandomSortField" indexed="true" />

    <!-- 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 text type for English text where stopwords and synonyms are managed using the REST API -->
    <fieldType name="managed_en" class="solr.TextField" positionIncrementGap="100">
      <analyzer>
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.ManagedStopFilterFactory" managed="english" />
        <filter class="solr.ManagedSynonymFilterFactory" managed="english" />
      </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" />
        <!-- 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" />
        <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"/>
        <!-- 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.
        -->
        <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"/>
  <!-- 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"
                />
        <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.
        -->
        <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"/>
        <!-- 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" />
        <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://docs.oracle.com/javase/8/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>

    <!-- 
      Example of using PathHierarchyTokenizerFactory at index time, so
      queries for paths match documents at that path, or in descendent paths
    -->
    <fieldType name="descendent_path" class="solr.TextField">
      <analyzer type="index">
  <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
      </analyzer>
      <analyzer type="query">
  <tokenizer class="solr.KeywordTokenizerFactory" />
      </analyzer>
    </fieldType>
    <!-- 
      Example of using PathHierarchyTokenizerFactory at query time, so
      queries for paths match documents at that path, or in ancestor paths
    -->
    <fieldType name="ancestor_path" class="solr.TextField">
      <analyzer type="index">
  <tokenizer class="solr.KeywordTokenizerFactory" />
      </analyzer>
      <analyzer type="query">
  <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
      </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"/>

    <!-- 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="0.001" distanceUnits="kilometers" />

    <!-- Spatial rectangle (bounding box) field. It supports most spatial predicates, and has
     special relevancy modes: score=overlapRatio|area|area2D (local-param to the query).  DocValues is recommended for
     relevancy. -->
    <fieldType name="bbox" class="solr.BBoxField"
               geo="true" distanceUnits="kilometers" numberType="_bbox_coord" />
    <fieldType name="_bbox_coord" class="solr.TrieDoubleField" precisionStep="8" docValues="true" useDocValuesAsStored="false" stored="false" />

   <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
        Parameters:
          defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
          precisionStep:   Specifies the precisionStep for the TrieLong field used for the amount
          providerClass:   Lets you plug in other exchange provider backend:
                           solr.FileExchangeRateProvider is the default and takes one parameter:
                             currencyConfig: name of an xml file holding exchange rates
                           solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
                             ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
                             refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
   -->
    <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
             


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

    <!-- Arabic -->
    <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <!-- for any non-arabic -->
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
        <!-- normalizes ? to ?, etc -->
        <filter class="solr.ArabicNormalizationFilterFactory"/>
        <filter class="solr.ArabicStemFilterFactory"/>
      </analyzer>
    </fieldType>

    <!-- Bulgarian -->
    <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/> 
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" /> 
        <filter class="solr.BulgarianStemFilterFactory"/>       
      </analyzer>
    </fieldType>
    
    <!-- Catalan -->
    <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <!-- removes l', etc -->
        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" />
        <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>       
      </analyzer>
    </fieldType>
    
    <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
    <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
      <analyzer>
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <!-- normalize width before bigram, as e.g. half-width dakuten combine  -->
        <filter class="solr.CJKWidthFilterFactory"/>
        <!-- for any non-CJK -->
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.CJKBigramFilterFactory"/>
      </analyzer>
    </fieldType>

    <!-- Kurdish -->
    <fieldType name="text_ckb" class="solr.TextField" positionIncrementGap="100">
      <analyzer>
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.SoraniNormalizationFilterFactory"/>
        <!-- for any latin text -->
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ckb.txt"/>
        <filter class="solr.SoraniStemFilterFactory"/>
      </analyzer>
    </fieldType>

    <!-- Czech -->
    <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" />
        <filter class="solr.CzechStemFilterFactory"/>       
      </analyzer>
    </fieldType>
    
    <!-- Danish -->
    <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
        <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>       
      </analyzer>
    </fieldType>
    
    <!-- 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" />
        <filter class="solr.GermanNormalizationFilterFactory"/>
        <filter class="solr.GermanLightStemFilterFactory"/>
        <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
      </analyzer>
    </fieldType>
    
    <!-- Greek -->
    <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <!-- greek specific lowercase for sigma -->
        <filter class="solr.GreekLowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
        <filter class="solr.GreekStemFilterFactory"/>
      </analyzer>
    </fieldType>
    
    <!-- Spanish -->
    <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
        <filter class="solr.SpanishLightStemFilterFactory"/>
        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
      </analyzer>
    </fieldType>
    
    <!-- Basque -->
    <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" />
        <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
      </analyzer>
    </fieldType>
    
    <!-- Persian -->
    <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
      <analyzer>
        <!-- for ZWNJ -->
        <charFilter class="solr.PersianCharFilterFactory"/>
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.ArabicNormalizationFilterFactory"/>
        <filter class="solr.PersianNormalizationFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" />
      </analyzer>
    </fieldType>
    
    <!-- Finnish -->
    <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
        <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
        <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
      </analyzer>
    </fieldType>
    
    <!-- French -->
    <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <!-- removes l', etc -->
        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
        <filter class="solr.FrenchLightStemFilterFactory"/>
        <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
      </analyzer>
    </fieldType>
    
    <!-- Irish -->
    <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <!-- removes d', etc -->
        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
        <!-- removes n-, etc. position increments is intentionally false! -->
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
        <filter class="solr.IrishLowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/>
        <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
      </analyzer>
    </fieldType>
    
    <!-- Galician -->
    <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" />
        <filter class="solr.GalicianStemFilterFactory"/>
        <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
      </analyzer>
    </fieldType>
    
    <!-- Hindi -->
    <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <!-- normalizes unicode representation -->
        <filter class="solr.IndicNormalizationFilterFactory"/>
        <!-- normalizes variation in spelling -->
        <filter class="solr.HindiNormalizationFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
        <filter class="solr.HindiStemFilterFactory"/>
      </analyzer>
    </fieldType>
    
    <!-- Hungarian -->
    <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
        <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
        <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->   
      </analyzer>
    </fieldType>
    
    <!-- Armenian -->
    <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" />
        <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
      </analyzer>
    </fieldType>
    
    <!-- Indonesian -->
    <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" />
        <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
        <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
      </analyzer>
    </fieldType>
    
    <!-- Italian -->
    <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <!-- removes l', etc -->
        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
        <filter class="solr.ItalianLightStemFilterFactory"/>
        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
      </analyzer>
    </fieldType>
    
    <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)

         NOTE: If you want to optimize search for precision, use default operator AND in your query
         parser config with <solrQueryParser defaultOperator="AND"/> further down in this file.  Use 
         OR if you would like to optimize for recall (default).
    -->
    <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
      <analyzer>
      <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)

           Kuromoji has a search mode (default) that does segmentation useful for search.  A heuristic
           is used to segment compounds into its parts and the compound itself is kept as synonym.

           Valid values for attribute mode are:
              normal: regular segmentation
              search: segmentation useful for search with synonyms compounds (default)
            extended: same as search mode, but unigrams unknown words (experimental)

           For some applications it might be good to use search mode for indexing and normal mode for
           queries to reduce recall and prevent parts of compounds from being matched and highlighted.
           Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.

           Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
           model with your own entries for segmentation, part-of-speech tags and readings without a need
           to specify weights.  Notice that user dictionaries have not been subject to extensive testing.

           User dictionary attributes are:
                     userDictionary: user dictionary filename
             userDictionaryEncoding: user dictionary encoding (default is UTF-8)

           See lang/userdict_ja.txt for a sample user dictionary file.

           Punctuation characters are discarded by default.  Use discardPunctuation="false" to keep them.

           See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
        -->
        <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
        <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
        <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
        <filter class="solr.JapaneseBaseFormFilterFactory"/>
        <!-- Removes tokens with certain part-of-speech tags -->
        <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
        <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
        <filter class="solr.CJKWidthFilterFactory"/>
        <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" />
        <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
        <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
        <!-- Lower-cases romaji characters -->
        <filter class="solr.LowerCaseFilterFactory"/>
      </analyzer>
    </fieldType>
    
    <!-- Latvian -->
    <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" />
        <filter class="solr.LatvianStemFilterFactory"/>
      </analyzer>
    </fieldType>
    
    <!-- Dutch -->
    <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
        <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
        <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
      </analyzer>
    </fieldType>
    
    <!-- Norwegian -->
    <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
        <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
        <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory" variant="nb"/> -->
        <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory" variant="nb"/> -->
        <!-- The "light" and "minimal" stemmers support variants: nb=Bokm?l, nn=Nynorsk, no=Both -->
      </analyzer>
    </fieldType>
    
    <!-- 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>
    
    <!-- Romanian -->
    <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" />
        <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
      </analyzer>
    </fieldType>
    
    <!-- Russian -->
    <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
        <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
        <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
      </analyzer>
    </fieldType>
    
    <!-- Swedish -->
    <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
        <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
        <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
      </analyzer>
    </fieldType>
    
    <!-- Thai -->
    <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.ThaiTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" />
      </analyzer>
    </fieldType>
    
    <!-- Turkish -->
    <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
      <analyzer> 
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.ApostropheFilterFactory"/>
        <filter class="solr.TurkishLowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
        <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
      </analyzer>
    </fieldType>

    <!-- Pre-analyzed field type, allows inserting arbitrary token streams and stored values. -->
    <fieldType name="preanalyzed" class="solr.PreAnalyzedField">
      <!-- PreAnalyzedField's builtin index analyzer just decodes the pre-analyzed token stream. -->
      <analyzer type="query">
        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
      </analyzer>
    </fieldType>

  <!-- Similarity is the scoring routine for each document vs. a query.
       A custom Similarity or SimilarityFactory may be specified here, but 
       the default is fine for most applications.  
       For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
    -->
  <!--
     <similarity class="com.example.solr.CustomSimilarityFactory">
       <str name="paramkey">param value</str>
     </similarity>
    -->
    
    <fieldType name="text_ik" class="solr.TextField">
        <analyzer type="index">
                <tokenizer class="org.apache.lucene.analysis.ik.IKTokenizerFactory" useSmart="false"/>
        </analyzer>
        <analyzer type="query">
                <tokenizer class="org.apache.lucene.analysis.ik.IKTokenizerFactory" useSmart="true"/>
        </analyzer>
    </fieldType>
    
<!--   <fieldtype name="text_pinyin" class="solr.TextField">
   <analyzer type="index">
      <tokenizer class="org.apache.lucene.analysis.ik.IKTokenizerFactory" useSmart="false"/>
        <filter class="org.liangbl.solr.analysis.PinyinTransformTokenFilterFactory" isOutChinese="true" 
          outputFormat="both" minTermLength="1"/>
        <filter class="org.liangbl.solr.analysis.PinyinNGramTokenFilterFactory" minGramSize="1" maxGramSize="20"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
        <filter class="solr.LowerCaseFilterFactory" />
        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
      </analyzer>
      <analyzer type="query">
        <tokenizer class="org.apache.lucene.analysis.ik.IKTokenizerFactory" useSmart="false"/>
        <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> -->
    
    <fieldtype name="text_pinyin" class="solr.TextField">
     <analyzer type="index">
        <tokenizer class="solr.KeywordTokenizerFactory"/>
        <filter class="com.gomehigo.search.analyzers.PinyinTransformTokenFilterFactory" isOutChinese="false" outputFormat="full" minTermLength="1"/>
        <filter class="com.gomehigo.search.analyzers.PinyinNGramTokenFilterFactory" minGram="1" maxGram="20" isNGramChinese="false" isNGramNumber="true"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
        <filter class="solr.LowerCaseFilterFactory" />
        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
      </analyzer>
      <analyzer type="query">
        <tokenizer class="solr.KeywordTokenizerFactory"/>
        <filter class="com.gomehigo.search.analyzers.PinyinTransformTokenFilterFactory" isOutChinese="false" outputFormat="full" minTermLength="1"/>
        <filter class="com.gomehigo.search.analyzers.PinyinNGramTokenFilterFactory" minGram="1" maxGram="20" isNGramChinese="false" isNGramNumber="true"/>
        <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>

   
</schema>

 4. 这个配置和第3步一起配置 solr-data-config.xml

<!--
  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.
  -->

<dataConfig>
  <dataSource name="ds-1" type="JdbcDataSource" driver="com.mysql.jdbc.Driver" url="jdbc:mysql://127.0.0.1:3306/cms?useUnicode=true&amp;characterEncoding=UTF-8" user="root" password="root"/>
  <document>
    <entity name="pinyin"  pk="ID" dataSource="ds-1" query="select * from cms_solr_XXX_pinyin  where del_flag=0 and type=0" deltaQuery="select ID from cms_solr_XXX_pinyin  where modify_date > '${dataimporter.last_index_time}' and del_flag=0 and type=0">
         <field column="ID" name="id" />
         <field column="NAME" name="name" />
         <field column="PINYIN" name="pinyin" />
         <field column="DIVISION_CODE" name="division_code" />
         <field column="FIRST_SPELL" name="first_spell" />
         <field column="ABBRE" name="abbre" />
         <field column="POINT_NUM" name="point_num" />
         <field column="SCORE_NUM" name="score_num" />
         <field column="TYPE" name="type" />
         <field column="DIV_FLG" name="div_flg" />
         <field column="CREATE_DATE" name="create_date" />
         <field column="MODIFY_DATE" name="modify_date" />
     </entity>
  </document>
</dataConfig>