solr之schema.xml中文翻译

本是古典何须时尚 2022-07-21 05:59 174阅读 0赞

译者：张春玲  
原文地址：[http://blog.csdn.net/zcl\_love\_wx/article/details/51907488][http_blog.csdn.net_zcl_love_wx_article_details_51907488]  
  
![这里写图片描述][20160715162018235]  
翻译中……………  
声明：faceting我也一直不清楚在solr到底表示什么，以下遇到该词我也无能为力。

# 了解 #

此时solr已经更新到6了，此篇翻译入门学习之用是够了。  
1. schema.xml文件是solr的schema文件，在solr\_home的conf目录下。  
2. 关于schema.xml的英文讲解链接：[http://wiki.apache.org/solr/SchemaXml][http_wiki.apache.org_solr_SchemaXml]  
3. [约定优于配置][Link 1] ([https://zh.wikipedia.org/wiki/%E7%BA%A6%E5%AE%9A%E4%BC%98%E4%BA%8E%E9%85%8D%E7%BD%AE][Link 1]) ：

# schema.xml文件 #

字段名由字母数字下划线组成，且不能以数字开头。两端为下划线的字段为保留字段，如(`_version_`)。

<?xml version="1.0" encoding="UTF-8" ?>
    
    
    
    
    <schema name="example-DIH-solr" version="1.5">
      
     
    
    
      <field name="_version_" type="long" indexed="true" stored="true"/>
    
      
      <field name="_root_" type="string" indexed="true" stored="false"/>
    
      
      <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" /> 
    
       <field name="sku" type="text_en_splitting_tight" indexed="true" stored="true" omitNorms="true"/>
       <field name="name" type="text_general" indexed="true" stored="true"/>
       <field name="manu" type="text_general" indexed="true" stored="true" omitNorms="true"/>
       <field name="cat" type="string" indexed="true" stored="true" multiValued="true"/>
       <field name="features" type="text_general" indexed="true" stored="true" multiValued="true"/>
       <field name="includes" type="text_general" indexed="true" stored="true" termVectors="true" termPositions="true" termOffsets="true" />
    
       <field name="weight" type="float" indexed="true" stored="true"/>
       <field name="price" type="float" indexed="true" stored="true"/>
       <field name="popularity" type="int" indexed="true" stored="true" />
       <field name="inStock" type="boolean" indexed="true" stored="true" />
    
       <field name="store" type="location" indexed="true" stored="true"/>
    
       
       <field name="title" type="text_general" indexed="true" stored="true" multiValued="true"/>
       <field name="subject" type="text_general" indexed="true" stored="true"/>
       <field name="description" type="text_general" indexed="true" stored="true"/>
       <field name="comments" type="text_general" indexed="true" stored="true"/>
       <field name="author" type="text_general" indexed="true" stored="true"/>
       <field name="keywords" type="text_general" indexed="true" stored="true"/>
       <field name="category" type="text_general" indexed="true" stored="true"/>
       <field name="resourcename" type="text_general" indexed="true" stored="true"/>
       <field name="url" type="text_general" indexed="true" stored="true"/>
       <field name="content_type" type="string" indexed="true" stored="true" multiValued="true"/>
       <field name="last_modified" type="date" indexed="true" stored="true"/>
       <field name="links" type="string" indexed="true" stored="true" multiValued="true"/>
    
       
        <field name="content" type="text_general" indexed="false" stored="true" multiValued="true"/>
    
        
        <field name="text" type="text_general" indexed="true" stored="false" multiValued="true"/>
    
    catchall text field that indexes tokens both normally and in reverse for efficient
            leading wildcard queries
       
         <field name="text_rev" type="text_general_rev" indexed="true" stored="false" multiValued="true"/>
    
      
       <field name="manu_exact" type="string" indexed="true" stored="false"/>
    
       <field name="payloads" type="payloads" indexed="true" stored="true"/>
    
    
       
    
    
    //译者注：所谓动态字段（Dynamic Field）就是不用指定具体的名称，只要定义字段名称的规则。
    //动态字段允许 solr 去索引没有在 schema 中 明确定义 的字段。
    //假设你忘定义某个字段了，但只要该字段符合动态字段的定义规则就一样能被索引。
    //假设schema中定义了一个叫*_i的动态字段，当你要索引一个在schema中没有（忘记）定义的 myField_i 字段时，myField_i 能够被索引到。
           
       <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"/>
    
       
       <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"/>
    
       
       <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="text_general" indexed="true" stored="true" multiValued="true"/>
    
       <dynamicField name="random_*" type="random" />
    
       
        
    
    
        
        <uniqueKey>id</uniqueKey>
    
        
    
        
    
    
    //译者注：copyField 将多个字段的内容添加到一个字段中。
    //source属性 表示要复制的属性
    //dest属性 表示要复制到哪个字段
    //source和destination都支持通配符
    //还有一个maxChars属性 表示复制内容的最大字数
        
    
       <copyField source="cat" dest="text"/>
       <copyField source="name" dest="text"/>
       <copyField source="manu" dest="text"/>
       <copyField source="features" dest="text"/>
       <copyField source="includes" dest="text"/>
       <copyField source="manu" dest="manu_exact"/>
    
       
       <copyField source="price" dest="price_c"/>
    
       
       <copyField source="title" dest="text"/>
       <copyField source="author" dest="text"/>
       <copyField source="description" dest="text"/>
       <copyField source="keywords" dest="text"/>
       <copyField source="content" dest="text"/>
       <copyField source="content_type" dest="text"/>
       <copyField source="resourcename" dest="text"/>
       <copyField source="url" dest="text"/>
    
       
       <copyField source="author" dest="author_s"/>
    
        
        
    
        
        
    
    
    
    
    //译者注：fieldType告诉solr如何去处理某个字段的数据，以及在查询这个字段地如何处理。
    //class其实就是引用的java类，说有该字段的类型
    //如果FieldType 是 TextFiled类型，则还有analysis属性
        
    
        
        <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
    
        
        <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
    
        
    
    
    //译者注：
    //Solr至少有五种不同的域类型来保存一个整型，如果你算上string类型，那就是六种！
    //float，double，long和date也是至少有五种类型。以"Trie"开头的类型可以满足90%以上的需求。
    以Integer为例：
    //  tieIntField（设置precisionStep=0），通常称为"int"。它对大部分应用场景都是适合的。
    //  tieIntField（设置precisionStep>0），通常称为"tint"。如果你想在很多值的域上进行数值区间查询（包括facet区间），那么这种域类型在查询时有着极好的性能，但需要在索引时多消耗一些索引空间和时间。 
    //在Solr的示例配置中数值类型的precisionStep设置为8，date类型为6，建义使用这种默认设置。因为如果你选择更小的precisionStep值（但都>0），会导致Solr会为提高区间查询性能而增加索引的空间和时间。
    //  srtableIntField，通常称为 "sint"。与Trie相似（precisionStep=0），这个类型还支持sortMissingFirst和SortMissingLast属性。
    //  intField，通常称为 "pint"。过时不用了。
    //  BCDIntFIeld（Binary Coded Decimal）。
    
    //所有的数值类型都按它们的数值排序而不是按字典序排序。
    //ExternalFileField类型是用于处理要进行排序或影响打分的域变化很快的情况的（比如，按投票或是点击率排序），用这种类型不用再对文档建索引。
    
         
        <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
        <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
        <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
        <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
    
        
    
        <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
        <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
        <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
        <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
    
    
         
        <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
    
        
        <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
    
    
        
        <fieldType name="binary" class="solr.BinaryField"/>
    
        
        <fieldType name="random" class="solr.RandomSortField" indexed="true" />
    
    
        
    
         
    
        
        <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
          <analyzer>
            <tokenizer class="solr.WhitespaceTokenizerFactory"/>
          </analyzer>
        </fieldType>
    
         
        <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
          <analyzer type="index">
            <tokenizer class="solr.StandardTokenizerFactory"/>
            <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
            
            <filter class="solr.LowerCaseFilterFactory"/>
          </analyzer>
          <analyzer type="query">
            <tokenizer class="solr.StandardTokenizerFactory"/>
            <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
            <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
            <filter class="solr.LowerCaseFilterFactory"/>
          </analyzer>
        </fieldType>
    
    
         
        <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
          <analyzer type="index">
            <tokenizer class="solr.StandardTokenizerFactory"/>
            
            
            <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt" />
            <filter class="solr.LowerCaseFilterFactory"/>
            <filter class="solr.EnglishPossessiveFilterFactory"/>
            <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
      
            <filter class="solr.PorterStemFilterFactory"/>
          </analyzer>
          <analyzer type="query">
            <tokenizer class="solr.StandardTokenizerFactory"/>
            <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
            <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt" />
            <filter class="solr.LowerCaseFilterFactory"/>
            <filter class="solr.EnglishPossessiveFilterFactory"/>
            <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
      
            <filter class="solr.PorterStemFilterFactory"/>
          </analyzer>
        </fieldType>
    
    
         
        <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
          <analyzer type="index">
            <tokenizer class="solr.WhitespaceTokenizerFactory"/>
            
            
            <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt" />
            <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
            <filter class="solr.LowerCaseFilterFactory"/>
            <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
            <filter class="solr.PorterStemFilterFactory"/>
          </analyzer>
          <analyzer type="query">
            <tokenizer class="solr.WhitespaceTokenizerFactory"/>
            <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
            <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt" />
            <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
            <filter class="solr.LowerCaseFilterFactory"/>
            <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
            <filter class="solr.PorterStemFilterFactory"/>
          </analyzer>
        </fieldType>
    
    
         
        <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
          <analyzer>
            <tokenizer class="solr.WhitespaceTokenizerFactory"/>
            <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
            <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
            <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
            <filter class="solr.LowerCaseFilterFactory"/>
            <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
            <filter class="solr.EnglishMinimalStemFilterFactory"/>
            
            <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
          </analyzer>
        </fieldType>
    
        
        <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>
    
         
        
    
        
        <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
          <analyzer>
            
            <tokenizer class="solr.KeywordTokenizerFactory"/>
            
            <filter class="solr.LowerCaseFilterFactory" />
            
            <filter class="solr.TrimFilterFactory" />
            
            <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"/>
            
            <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
          </analyzer>
        </fieldType>
    
        
        <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
          <analyzer>
            <tokenizer class="solr.KeywordTokenizerFactory"/>
            <filter class="solr.LowerCaseFilterFactory" />
          </analyzer>
        </fieldType>
    
        
        <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>
         
        <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>
    
         
        <fieldType name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
    
        
        <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
    
        
        <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
    
        
        <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType" geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
    
       
        <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
    
    
    
       
    
        
        <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
          <analyzer> 
            <tokenizer class="solr.StandardTokenizerFactory"/>
            
            <filter class="solr.LowerCaseFilterFactory"/>
            <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
            
            <filter class="solr.ArabicNormalizationFilterFactory"/>
            <filter class="solr.ArabicStemFilterFactory"/>
          </analyzer>
        </fieldType>
    
        
        <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>
    
        
        <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
          <analyzer> 
            <tokenizer class="solr.StandardTokenizerFactory"/>
            
            <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>
    
        
        <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
          <analyzer>
            <tokenizer class="solr.StandardTokenizerFactory"/>
            
            <filter class="solr.CJKWidthFilterFactory"/>
            
            <filter class="solr.LowerCaseFilterFactory"/>
            <filter class="solr.CJKBigramFilterFactory"/>
          </analyzer>
        </fieldType>
    
        
        <fieldType name="text_ckb" class="solr.TextField" positionIncrementGap="100">
          <analyzer>
            <tokenizer class="solr.StandardTokenizerFactory"/>
            <filter class="solr.SoraniNormalizationFilterFactory"/>
            
            <filter class="solr.LowerCaseFilterFactory"/>
            <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ckb.txt"/>
            <filter class="solr.SoraniStemFilterFactory"/>
          </analyzer>
        </fieldType>
    
        
        <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>
    
        
        <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>
    
        
        <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"/>
            
            
          </analyzer>
        </fieldType>
    
        
        <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
          <analyzer> 
            <tokenizer class="solr.StandardTokenizerFactory"/>
            
            <filter class="solr.GreekLowerCaseFilterFactory"/>
            <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
            <filter class="solr.GreekStemFilterFactory"/>
          </analyzer>
        </fieldType>
    
        
        <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"/>
            
          </analyzer>
        </fieldType>
    
        
        <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>
    
        
        <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
          <analyzer>
            
            <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>
    
        
        <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"/>
            
          </analyzer>
        </fieldType>
    
        
        <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
          <analyzer> 
            <tokenizer class="solr.StandardTokenizerFactory"/>
            
            <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"/>
            
            
          </analyzer>
        </fieldType>
    
        
        <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
          <analyzer> 
            <tokenizer class="solr.StandardTokenizerFactory"/>
            
            <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
            
            <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>
    
        
        <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"/>
            
          </analyzer>
        </fieldType>
    
        
        <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
          <analyzer> 
            <tokenizer class="solr.StandardTokenizerFactory"/>
            <filter class="solr.LowerCaseFilterFactory"/>
            
            <filter class="solr.IndicNormalizationFilterFactory"/>
            
            <filter class="solr.HindiNormalizationFilterFactory"/>
            <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
            <filter class="solr.HindiStemFilterFactory"/>
          </analyzer>
        </fieldType>
    
        
        <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"/>
               
          </analyzer>
        </fieldType>
    
        
        <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>
    
        
        <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" />
            
            <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
          </analyzer>
        </fieldType>
    
        
        <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
          <analyzer> 
            <tokenizer class="solr.StandardTokenizerFactory"/>
            
            <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"/>
            
          </analyzer>
        </fieldType>
    
        
        <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
          <analyzer>
          
            <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
            
            
            <filter class="solr.JapaneseBaseFormFilterFactory"/>
            
            <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
            
            <filter class="solr.CJKWidthFilterFactory"/>
            
            <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" />
            
            <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
            
            <filter class="solr.LowerCaseFilterFactory"/>
          </analyzer>
        </fieldType>
    
        
        <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>
    
        
        <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>
    
        
        <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"/>
            
            
            
          </analyzer>
        </fieldType>
    
        
        <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"/>
            
            
            
          </analyzer>
        </fieldType>
    
        
        <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>
    
        
        <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"/>
            
          </analyzer>
        </fieldType>
    
        
        <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"/>
            
          </analyzer>
        </fieldType>
    
        
        <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
          <analyzer> 
            <tokenizer class="solr.StandardTokenizerFactory"/>
            <filter class="solr.LowerCaseFilterFactory"/>
            <filter class="solr.ThaiWordFilterFactory"/>
            <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" />
          </analyzer>
        </fieldType>
    
        
        <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>
    
      
      
    
    </schema>

[http_blog.csdn.net_zcl_love_wx_article_details_51907488]: http://blog.csdn.net/zcl_love_wx/article/details/51907488
[20160715162018235]: /images/20220720/616cd9d6d23849c98bebf740e923c1df.png
[http_wiki.apache.org_solr_SchemaXml]: http://wiki.apache.org/solr/SchemaXml
[Link 1]: https://zh.wikipedia.org/wiki/%E7%BA%A6%E5%AE%9A%E4%BC%98%E4%BA%8E%E9%85%8D%E7%BD%AE