Elasticsearch 父子关系维护和检索案例分享

yin_bp

浏览: 688078 次
性别:
来自: 长沙

最近访客更多访客>>

kennypho

ymgjava

luk7152

smile1979

博主相关

博客

微博

相册

留言

关于我

文章分类

社区版块

存档分类

elasticsearch bboss has_child has_parent

Elasticsearch 父子关系维护和检索案例分享,展示has_child和has_parent的基本用法。

本文涉及技术点：

1.删除和创建公司/雇员父子关系的索引表
2.bulk批量导入json格式数据
3.ormapping方式bulk批量导入数据
4.采用@ESId指定文档_id
5.采用@ESParentId制定子文档的parent信息
6.基本的has_child和has_parent公司/雇员父子关系检索

1.准备工作
参考文档《高性能elasticsearch ORM开发库使用介绍》导入和配置es客户端

2.定义dsl文档
建立dsl配置文件-esmapper/indexparentchild.xml

<properties>
    <!--
    本案例适用于es 2.x,5.x
    创建包含员工类型和公司类型的公司索引表
    -->
    <property name="createCompanyEmployeeIndice">
        <![CDATA[{
            "settings": {
                "number_of_shards": 6,
                "index.refresh_interval": "5s"
            },
            "mappings": {
                "company": { ##公司
                    "properties": {
                        "name": {
                            "type": "text",
                             "fields": { ##dsl注释 定义精确查找的内部keyword字段
                                "keyword": {
                                    "type": "keyword"
                                }
                            }
                        },

                        "city": {
                            "type": "text",
                            "fields": { ##dsl注释 定义精确查找的内部keyword字段
                                "keyword": {
                                    "type": "keyword"
                                }
                            }
                        },
                        "country": {
                            "type": "text",
                            "fields": { ##dsl注释 定义精确查找的内部keyword字段
                                "keyword": {
                                    "type": "keyword"
                                }
                            }
                        },
                        "companyId": {
                            "type": "keyword"
                        }
                    }
                },
                "employee":
                 { ##雇员
                     "_parent": {##定义雇员和公司父子关联关系
                        "type": "company"
                    },
                    "_routing": {
                        "required": false
                    },
                    "properties": {

                        "name": {
                            "type": "text",
                             "fields": { ##dsl注释 定义精确查找的内部keyword字段
                                "keyword": {
                                    "type": "keyword"
                                }
                            }
                        },
                        "birthday": {
                             "type": "date",
                              "format":"yyyy-MM-dd||epoch_millis"
                        },
                        "hobby": {
                            "type": "text",
                            "fields": { ##dsl注释 定义精确查找的内部keyword字段
                                "keyword": {
                                    "type": "keyword"
                                }
                            }
                        },
                        "companyId": {
                            "type": "keyword"
                        },
                        "employId": {
                            "type": "keyword"
                        }
                    }
                }

              }
        }]]>
    </property>
    <!--
    导入公司信息：
    -->
    <property name="bulkImportCompanyData">
        <![CDATA[
            { "index": { "_id": "london" }}
            { "name": "London Westminster", "city": "London", "country": "UK" ,"companyId":"london"}
            { "index": { "_id": "liverpool" }}
            { "name": "Liverpool Central", "city": "Liverpool", "country": "UK" ,"companyId":"liverpool"}
            { "index": { "_id": "paris" }}
            { "name": "Champs Élysées", "city": "Paris", "country": "France","companyId":"paris" }
        ]]>
    </property>
    <!--
   导入雇员信息：
   -->
    <property name="bulkImportEmployeeData">
        <![CDATA[
            { "index": { "_id": 1, "parent": "london" }}
            { "name": "Alice Smith", "birthday": "1970-10-24", "hobby": "hiking" ,"companyId":"london","employeeId":1 }
            { "index": { "_id": 2, "parent": "london" }}
            { "name": "Mark Thomas", "birthday": "1982-05-16", "hobby": "diving" ,"companyId":"london","employeeId":2}
            { "index": { "_id": 3, "parent": "liverpool" }}
            { "name": "Barry Smith", "birthday": "1979-04-01", "hobby": "hiking" ,"companyId":"liverpool","employeeId":3}
            { "index": { "_id": 4, "parent": "paris" }}
            { "name": "Adrien Grand", "birthday": "1987-05-11", "hobby": "horses" ,"companyId":"paris","employeeId":4}
            { "index": { "_id": 5, "parent": "paris" }}
            { "name": "Adrien Green", "birthday": "1977-05-12", "hobby": "dancing" ,"companyId":"paris","employeeId":5}
        ]]>
    </property>
    <!--出生日期为条件检索公司信息-->
    <property name="hasChildSearchByBirthday">
        <![CDATA[
            {
              "query": {
                "has_child": {
                  "type": "employee",
                  "query": {
                    "range": {
                      "birthday": {
                        "gte": #[birthday]
                      }
                    }
                  }
                }
              }
            }
        ]]>
    </property>
    <!--姓名为条件检索公司信息-->
    <property name="hasChildSearchByName">
        <![CDATA[
            {
              "query": {
                "has_child": {
                  "type":       "employee",
                  "score_mode": "max",
                  "query": {
                    "match": {
                      "name": #[name]
                    }
                  }
                }
              }
            }
        ]]>
    </property>
    <!--最小员工数为条件检索公司信息-->
    <property name="hasChildSearchByMinChild">
        <![CDATA[
            {
                "query": {
                    "has_child": {
                      "type":  "employee",
                      "min_children": #[min_children],
                      "query": {
                        "match_all": {}
                      }
                    }
                }
            }
        ]]>
    </property>

    <!--检索员工信息-->
    <property name="hasParentSearchByCountry">
        <![CDATA[
            {
              "query": {
                "has_parent": {
                  "type": "company",
                  "query": {
                    "match": {
                      "country": #[country]
                    }
                  }
                }
              }
            }
        ]]>
    </property>
</properties>

3.实现has_child和has_parent检索
首先创建带公司和雇员关系的索引结构

public void createIndice(){
		ClientInterface clientUtil = ElasticSearchHelper.getConfigRestClientUtil("esmapper/indexparentchild.xml");
		try {
			//删除mapping
			clientUtil.dropIndice("company");
		} catch (ElasticSearchException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
		//创建mapping
		clientUtil.createIndiceMapping("company","createCompanyEmployeeIndice");
	}

然后通过bulk导入测试需要的公司和雇员数据，本案例通过加载配置文件中的dsl json data导入公司和雇员数据：

public void importData(){
		ClientInterface clientUtil = ElasticSearchHelper.getConfigRestClientUtil("esmapper/indexparentchild.xml");

		//导入公司数据,并且实时刷新，测试需要，实际环境不要带refresh
		clientUtil.executeHttp("company/company/_bulk?refresh","bulkImportCompanyData",ClientUtil.HTTP_POST);
		//导入雇员数据,并且实时刷新，测试需要，实际环境不要带refresh
		clientUtil.executeHttp("company/employee/_bulk?refresh","bulkImportEmployeeData",ClientUtil.HTTP_POST);
	}

如果需要根据List集合批量导入测试数据，则参考以下方法：

/**
	 * 通过List集合导入雇员和公司数据
	 */
	public void importDataFromBeans()  {
		ClientInterface clientUtil = ElasticSearchHelper.getRestClientUtil();

		//导入公司数据,并且实时刷新，测试需要，实际环境不要带refresh
		List<Company> companies = buildCompanies();
		clientUtil.addDocuments("company","company",companies,"refresh");

		//导入雇员数据,并且实时刷新，测试需要，实际环境不要带refresh
		List<Employee> employees = buildEmployees();
		clientUtil.addDocuments("company","employee",employees,"refresh");
	}

List<Company>和List<Employee>列表分别对应需要批量导入的公司数据和雇员数据。需要特别说明的是Company和Employee这两个对象采用了注解@ESId来标注文档_id属性，采用@ESParentId属性来标注雇员和公司的关联属性：

public class Company extends ESBaseData {
	private String name;
	/**
	 * 将companyId作为索引_id的值
	 */
	@ESId
	private String companyId;
。。。。。。

public class Employee extends ESBaseData {
	/**
	 * 通过ESId注解将employeeId指定为雇员的文档_id
	 */
	@ESId
	private int employeeId;
	/**
	 * 通过ESParentId注解将companyId指定为雇员的parent属性，对应Company中的文档_id的值
	 */
	@ESParentId
	private String companyId;

接下来实现has_child和has_parent检索功能

/**
	 * 通过雇员生日检索公司信息
	 */
	public void hasChildSearchByBirthday(){

		ClientInterface clientUtil = ElasticSearchHelper.getConfigRestClientUtil("esmapper/indexparentchild.xml");
		Map<String,Object> params = new HashMap<String,Object>();
		params.put("birthday","1980-01-01");
		ESDatas<Company> escompanys = clientUtil.searchList("company/company/_search","hasChildSearchByBirthday",params,Company.class);
		List<Company> companyList = escompanys.getDatas();//获取符合条件的公司
		long totalSize = escompanys.getTotalSize();
	}

	/**
	 * 通过雇员姓名检索公司信息
	 */
	public void hasChildSearchByName(){

		ClientInterface clientUtil = ElasticSearchHelper.getConfigRestClientUtil("esmapper/indexparentchild.xml");
		Map<String,Object> params = new HashMap<String,Object>();
		params.put("name","Alice Smith");
		ESDatas<Company> escompanys = clientUtil.searchList("company/company/_search","hasChildSearchByName",params,Company.class);
		List<Company> companyList = escompanys.getDatas();//获取符合条件的公司
		long totalSize = escompanys.getTotalSize();

	}
	/**
	 * 通过雇员数量检索公司信息
	 */
	public void hasChildSearchByMinChild(){

		ClientInterface clientUtil = ElasticSearchHelper.getConfigRestClientUtil("esmapper/indexparentchild.xml");
		Map<String,Object> params = new HashMap<String,Object>();
		params.put("min_children",2);
		ESDatas<Company> escompanys = clientUtil.searchList("company/company/_search","hasChildSearchByMinChild",params,Company.class);
		List<Company> companyList = escompanys.getDatas();//获取符合条件的公司
		long totalSize = escompanys.getTotalSize();

	}
	/**
	 * 通过公司所在国家检索雇员信息
	 */
	public void hasParentSearchByCountry(){

		ClientInterface clientUtil = ElasticSearchHelper.getConfigRestClientUtil("esmapper/indexparentchild.xml");
		Map<String,Object> params = new HashMap<String,Object>();
		params.put("country","UK");
		ESDatas<Employee> escompanys = clientUtil.searchList("company/employee/_search","hasParentSearchByCountry",params,Employee.class);
		List<Employee> companyList = escompanys.getDatas();//获取符合条件的公司
		long totalSize = escompanys.getTotalSize();

	}

通过junit测试用例执行上述功能

@Test
	public void test(){
		createIndice();
		importData();
		hasChildSearchByBirthday();
		this.hasChildSearchByName();
		this.hasChildSearchByMinChild();
		this.hasParentSearchByCountry();
	}