SolrCloud 8.4嵌套文档索引查询问题及Schema配置需求

以下是适配Solr官方嵌套文档示例数据的基础JSON Schema配置，包含嵌套文档必需的核心字段及常见业务字段定义：

{
  "schema": {
    "name": "nested_docs_schema",
    "version": 1.6,
    "uniqueKey": "id",
    "fields": [
      {
        "name": "id",
        "type": "string",
        "stored": true,
        "required": true
      },
      {
        "name": "_root_",
        "type": "string",
        "stored": false,
        "indexed": true
      },
      {
        "name": "title",
        "type": "text_general",
        "stored": true,
        "indexed": true
      },
      {
        "name": "content",
        "type": "text_general",
        "stored": true,
        "indexed": true
      },
      {
        "name": "author",
        "type": "string",
        "stored": true,
        "indexed": true
      },
      {
        "name": "child_docs",
        "type": "child",
        "stored": true,
        "indexed": true,
        "docValues": false
      },
      {
        "name": "type",
        "type": "string",
        "stored": true,
        "indexed": true,
        "multiValued": false
      }
    ],
    "copyFields": [],
    "dynamicFields": [
      {
        "name": "*_s",
        "type": "string",
        "stored": true,
        "indexed": true
      },
      {
        "name": "*_t",
        "type": "text_general",
        "stored": true,
        "indexed": true
      }
    ]
  }
}

关键配置说明 #

• _root_：必填字段，用于维护父文档与子文档的层级关联，Solr会自动填充该字段值为父文档的id
• child_docs：child类型字段，用于存储嵌套的子文档集合
• type字段：用于区分父/子文档类型（比如父文档标记为article，子文档标记为comment），方便查询时过滤

可选XML格式Schema配置 #

如果需要XML格式，以下是对应配置：

<?xml version="1.0" encoding="UTF-8"?>
<schema name="nested_docs_schema" version="1.6">
  <uniqueKey>id</uniqueKey>
  
  <fields>
    <field name="id" type="string" stored="true" required="true"/>
    <field name="_root_" type="string" stored="false" indexed="true"/>
    <field name="title" type="text_general" stored="true" indexed="true"/>
    <field name="content" type="text_general" stored="true" indexed="true"/>
    <field name="author" type="string" stored="true" indexed="true"/>
    <field name="child_docs" type="child" stored="true" indexed="true" docValues="false"/>
    <field name="type" type="string" stored="true" indexed="true" multiValued="false"/>
    
    <!-- 动态字段 -->
    <dynamicField name="*_s" type="string" stored="true" indexed="true"/>
    <dynamicField name="*_t" type="text_general" stored="true" indexed="true"/>
  </fields>
  
  <copyField source="*" dest="_text_"/>
</schema>

索引示例数据参考 #

你可以用以下格式提交嵌套文档数据（适配上述Schema）：

[
  {
    "id": "article_1",
    "type": "article",
    "title": "Solr嵌套文档入门",
    "content": "本文介绍Solr嵌套文档的使用方法",
    "author": "Solr官方",
    "child_docs": [
      {
        "id": "comment_1",
        "type": "comment",
        "content": "这个教程很有用",
        "author": "用户A"
      },
      {
        "id": "comment_2",
        "type": "comment",
        "content": "终于搞懂嵌套文档了",
        "author": "用户B"
      }
    ]
  }
]

基础查询示例 #

• 查询包含特定子文档内容的父文档：
  q={!child of='type:article'}content:有用
• 查询所有子文档：
  q=type:comment&fl=id,author,content

内容的提问来源于stack exchange，提问作者Pedro Gomes