02_Solr域的类型和分类、中文分词器

域的类型和分类

域的分类

  • 普通域:string long 等
  • 动态域:起到模糊匹配的效果,可以模糊匹配没有定义过的域名
      例如:xxxx这个域名没有定义,但是xxxx_s这个域名模糊匹配了*_s这个域,所以相当于xxxx_s这个域定义了
  • 主键域:<uniqueKey>id</uniqueKey> 一般主键域就用默认的这个就可以不需要更改或者添加
  • 复制域: 复制域用于查询的时候从多个域中进行查询,这样可以将多个域复制到某一个统一的域中,然后搜索的时候从这个统一的域中进行查询,就相当于从多个域中查询了.

域名field

普通域

   <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"/>
   <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"/>
  • type :类型
  • indexed:是否索引
  • stored:是否存储
  • required:是否是必须,因为id的required=true,所以我们在上一节删除id报错
  • multiValued:是否可以存放多值,true,表示改域可以存放数组

动态域

   <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="*_coordinate"  type="tdouble" indexed="true"  stored="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"/>
   <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" />

主键域

<uniqueKey>id</uniqueKey>

复制域

   <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"/>

域的类型

    <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
    <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
    <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
    <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
    <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
    <fieldType name="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" />

中文分词器

  • 停止tomcat
  • 将中文分词器的jar包导入solr项目的lib目录
  • WEB-INF目录下创建classes目录,并将IK分词器的配置文件拷贝到改目录下

  • 进入solrhome的conf目录
    D:\tools\tomcat\solr\collection1\conf
  • 编辑schema.xml
    在最后面添加,注意:此文件中不能写中文
    <!-- IKAnalyzer-->
    <fieldType name="text_ik" class="solr.TextField">
      <analyzer class="org.wltea.analyzer.lucene.IKAnalyzer"/>
    </fieldType>
  • 定义field,指定field的type属性为text_ik
   <!--IKAnalyzer Field-->
   <field name="title_ik" type="text_ik" indexed="true" stored="true" />
   <field name="content_ik" type="text_ik" indexed="true" stored="false" multiValued="true"/>
  • 重新启动tomcat

  • 进入web界面,查看分词效果


域是否存储和是否索引无关, 索引后就能查询,不索引就不能根据这个域搜索,存储后就能取出来里面的内容,不存储就取不出这个域内容

推荐阅读更多精彩内容