C/C++教程
elasticsearch支持大table格式数据的搜索
本文主要是介绍elasticsearch支持大table格式数据的搜索，对大家解决编程问题具有一定的参考价值，需要的程序猿们随着小编来一起学习吧！
一、问题源起
数据情况
TableMeta， 保存table的元数据，通过fileId关联具体的GridFS文件；
| id | name | creator | fileId |
|---|---|---|---|
| 1 | table1 | mango | f1 |
| 2 | table2 | mango | f2 |
table内包含列名和具体的行数据；
不同类型的table，列的名字和数量都可能不同；
from fport to toport location 192.168.1.1 11 192.168.1.12 11 chaoyang 192.168.1.2 22 192.168.1.13 22 tongzhou
搜索要求
支持所有类型的table的搜索；
支持全字段的搜索；
只返回表内命中的行，并进行高亮；
二、开发环境
elasticsearch 6.8.12 java 12.0.2 2019-07-16 Java(TM) SE Runtime Environment (build 12.0.2+10) Java HotSpot(TM) 64-Bit Server VM (build 12.0.2+10, mixed mode, sharing)
三、elastic search对array的支持情况
扁平化数组元素
默认情况下elastic search会将数组内部对象的字段进行扁平化处理，这样就会丢失掉元素的独立性。
直接index一个文档
PUT my_array_index/_doc/1
{
"group" : "fans",
"user" : [
{
"first" : "John",
"last" : "Smith"
},
{
"first" : "Alice",
"last" : "White"
}
]
}
{
"_index":"my_array_index",
"_type":"_doc",
"_id":"1",
"_version":1,
"result":"created",
"_shards":{
"total":2,
"successful":1,
"failed":0
},
"_seq_no":0,
"_primary_term":1
}
elastic search 内部会将文档转化为如下形式再进行索引
{
"group" : "fans",
"user.first" : [ "alice", "john" ],
"user.last" : [ "smith", "white" ]
}
扁平化处理将所有数组元素对象的相同字段值合并到一起作为一个数组，这样就丢失了user.first和user.last之间的对应关系，类似下边的查询即使没有Alice Smith这个人也可以命中
GET my_index/_search
{
"query": {
"bool": {
"must": [
{ "match": { "user.first": "Alice" }},
{ "match": { "user.last": "Smith" }}
]
}
}
}
{
"took":2,
"timed_out":false,
"_shards":{
"total":5,
"successful":5,
"skipped":0,
"failed":0
},
"hits":{
"total":1,
"max_score":0.5753642,
"hits":[
{
"_index":"my_array_index",
"_type":"_doc",
"_id":"1",
"_score":0.5753642,
"_source":{
"group":"fans",
"user":[
{
"first":"John",
"last":"Smith"
},
{
"first":"Alice",
"last":"White"
}
]
}
}
]
}
}
使用nested数据类型文档化数组元素
elastic search内部提供了nested数据类型，可以将数组元素作为单独的隐藏的内部文档进行索引，从而保持文档之间的独立性；
将字段映射为nested类型
PUT my_nested_index
{
"mappings": {
"_doc": {
"properties": {
"user": {
"type": "nested"
}
}
}
}
}
{
"acknowledged":true,
"shards_acknowledged":true,
"index":"my_nested_index"
}
index文档
PUT my_nested_index/_doc/1
{
"group" : "fans",
"user" : [
{
"first" : "John",
"last" : "Smith"
},
{
"first" : "Alice",
"last" : "White"
}
]
}
{
"_index":"my_nested_index",
"_type":"_doc",
"_id":"1",
"_version":1,
"result":"created",
"_shards":{
"total":2,
"successful":1,
"failed":0
},
"_seq_no":0,
"_primary_term":1
}
elastic search提供了单独的nested query 来支持nested类型
GET my_nested_index/_search
{
"query": {
"nested": {
"path": "user",
"query": {
"bool": {
"must": [
{ "match": { "user.first": "Alice" }},
{ "match": { "user.last": "Smith" }}
]
}
}
}
}
}
{
"took":3,
"timed_out":false,
"_shards":{
"total":5,
"successful":5,
"skipped":0,
"failed":0
},
"hits":{
"total":0,
"max_score":null,
"hits":[
]
}
}
nested query提供了inner_hits类支持字段高亮，从高亮信息中可以看到，offset字段指出了命中了数组中的第几个元素；
GET my_nested_index/_search
{
"query": {
"nested": {
"path": "user",
"query": {
"bool": {
"should": [
{ "match": { "user.first": "Alice" }},
{ "match": { "user.last": "smith" }}
]
}
},
"inner_hits": {
"highlight": {
"fields": {
"*": {}
}
}
}
}
}
}
{
"took":8,
"timed_out":false,
"_shards":{
"total":5,
"successful":5,
"skipped":0,
"failed":0
},
"hits":{
"total":1,
"max_score":0.6931472,
"hits":[
{
"_index":"my_nested_index",
"_type":"_doc",
"_id":"1",
"_score":0.6931472,
"_source":{
"group":"fans",
"user":[
{
"first":"John",
"last":"Smith"
},
{
"first":"Alice",
"last":"White"
}
]
},
"inner_hits":{
"user":{
"hits":{
"total":2,
"max_score":0.6931472,
"hits":[
{
"_index":"my_nested_index",
"_type":"_doc",
"_id":"1",
"_nested":{
"field":"user",
"offset":0
},
"_score":0.6931472,
"_source":{
"first":"John",
"last":"Smith"
},
"highlight":{
"user.last":[
"<em>Smith</em>"
]
}
},
{
"_index":"my_nested_index",
"_type":"_doc",
"_id":"1",
"_nested":{
"field":"user",
"offset":1
},
"_score":0.6931472,
"_source":{
"first":"Alice",
"last":"White"
},
"highlight":{
"user.first":[
"<em>Alice</em>"
]
}
}
]
}
}
}
}
]
}
}
总结
经过以上的研究可以看到，elastic search提供的nested数据类型基本满足我们的目标要求，接下来使用具体的table数据做进一步的研究；
四、使用nested数据类型索引Table数据
elastic search索引数据结构
| 字段名字 | 字段类型 | 描述 |
|---|---|---|
| id | string | 主键 |
| name | string | table的名字 |
| creator | string | 创建者 |
| content | (object) array | 行数据数组 |
elastic search mapping
PUT tables
{
"mappings": {
"_doc": {
"properties": {
"id": {
"type": "keyword"
},
"name": {
"type": "keyword"
},
"creator": {
"type": "keyword"
},
"content": {
"type": "nested"
}
}
}
}
}
{
"acknowledged": true,
"shards_acknowledged": true,
"index": "tables"
}
index 一个Table data
PUT tables/_doc/1
{
"id":"1",
"name":"table1",
"creator":"mango",
"content":[
{
"0":"192.168.1.1",
"1":"11",
"2":"192.168.1.12",
"3":"11",
"4":"chaoyang"
},
{
"0":"192.168.1.2",
"1":"22",
"2":"192.168.1.13",
"3":"22",
"4":"tongzhou"
},
{
"0":"192.168.3",
"1":"33",
"2":"192.168.1.14",
"3":"33",
"4":"daxing"
}
]
}
{
"_index":"tables",
"_type":"_doc",
"_id":"1",
"_version":1,
"result":"created",
"_shards":{
"total":2,
"successful":1,
"failed":0
},
"_seq_no":0,
"_primary_term":1
}
search Table data
搜索所有列
限制只返回Table的元数据信息
限制只返回命中行的信息
返回命中行的高亮信息
post /tables/_search/
{
"from":0,
"size":20,
"_source":{
"excludes":[
"content"
]
},
"query":{
"nested":{
"path":"content",
"query":{
"query_string":{
"fields":[
"content.*"
],
"query":"tongzhou 192.168.1.1"
}
},
"inner_hits":{
"from":0,
"size":2,
"highlight":{
"fields":{
"*":{
}
}
}
}
}
}
}
{
"took":19,
"timed_out":false,
"_shards":{
"total":5,
"successful":5,
"skipped":0,
"failed":0
},
"hits":{
"total":1,
"max_score":0.9808292,
"hits":[
{
"_index":"tables",
"_type":"_doc",
"_id":"1",
"_score":0.9808292,
"_source":{
"creator":"mango",
"name":"table1",
"id":"1"
},
"inner_hits":{
"content":{
"hits":{
"total":2,
"max_score":0.9808292,
"hits":[
{
"_index":"tables",
"_type":"_doc",
"_id":"1",
"_nested":{
"field":"content",
"offset":0
},
"_score":0.9808292,
"_source":{
"0":"192.168.1.1",
"1":"11",
"2":"192.168.1.12",
"3":"11",
"4":"chaoyang"
},
"highlight":{
"content.0":[
"<em>192.168.1.1</em>"
]
}
},
{
"_index":"tables",
"_type":"_doc",
"_id":"1",
"_nested":{
"field":"content",
"offset":1
},
"_score":0.9808292,
"_source":{
"0":"192.168.1.2",
"1":"22",
"2":"192.168.1.13",
"3":"22",
"4":"tongzhou"
},
"highlight":{
"content.4":[
"<em>tongzhou</em>"
]
}
}
]
}
}
}
}
]
}
}
这篇关于elasticsearch支持大table格式数据的搜索的文章就介绍到这儿，希望我们推荐的文章对大家有所帮助，也希望大家多多支持为之网！
您可能喜欢
-
增量更新怎么做？-icode9专业技术文章分享11-23
-
压缩包加密方案有哪些？-icode9专业技术文章分享11-23
-
用shell怎么写一个开机时自动同步远程仓库的代码？-icode9专业技术文章分享11-23
-
webman可以同步自己的仓库吗？-icode9专业技术文章分享11-23
-
在 Webman 中怎么判断是否有某命令进程正在运行？-icode9专业技术文章分享11-23
-
如何重置new Swiper?-icode9专业技术文章分享11-23
-
oss直传有什么好处？-icode9专业技术文章分享11-23
-
如何将oss直传封装成一个组件在其他页面调用时都可以使用？-icode9专业技术文章分享11-23
-
怎么使用laravel 11在代码里获取路由列表？-icode9专业技术文章分享11-23
-
怎么实现ansible playbook 备份代码中命名包含时间戳功能？-icode9专业技术文章分享11-22
-
ansible 的archive 参数是什么意思？-icode9专业技术文章分享11-22
-
ansible 中怎么只用archive 排除某个目录？-icode9专业技术文章分享11-22
-
exclude_path参数是什么作用？-icode9专业技术文章分享11-22
-
微信开放平台第三方平台什么时候调用数据预拉取和数据周期性更新接口？-icode9专业技术文章分享11-22
-
uniapp 实现聊天消息会话的列表功能怎么实现？-icode9专业技术文章分享11-22
栏目导航
