hive 操作elasticsearch
一,从hive 表格向elasticsearch 导入数据
1,首先,创建elasticsearch 索引,索引如下
curl -XPUT ‘10.81.179.209:9200/zebra_info_demo?pretty‘ -H ‘Content-Type: application/json‘ -d‘
{
"settings": {
"number_of_shards":5,
"number_of_replicas":2
},
"mappings": {
"zebra_info": {
"properties": {
"name" : {"type" : "text"},
"type": {"type": "text"},
"province": {"type": "text"},
"city": {"type": "text"},
"citycode": {"type": "text", "index": "no"},
"district": {"type": "text"},
"adcode": {"type": "text", "index": "no"},
"township": {"type": "text"},
"bausiness_circle": {"type": "text"},
"formatted_address": {"type": "text"},
"location": {"type": "geo_point"},
"extensions": {
"type": "nested",
"properties": {
"map_lat": {"type": "double", "index": "no"},
"map_lng": {"type": "double", "index": "no"},
"avg_price": {"type": "double", "index": "no"},
"shops": {"type":"short", "index": "no"},
"good_comments": {"type":"short", "index": "no"},
"lvl": {"type":"short", "index": "no"},
"leisure_type": {"type": "text", "index": "no"},
"fun_type": {"type": "text", "index": "no"},
"numbers": {"type": "short", "index": "no"}
}
}
}
}
}
}
‘
2,查看elasticsearch版本,下载相应的elasticsearch-hive-hadoop jar 包
可以用如下命令查看elastic search 的版本
本文版本5.6.9
到如下maven 官网下载jar 包。
https://repo.maven.apache.org/maven2/org/elasticsearch/elasticsearch-hadoop-hive/
选择正确的版本即可。
3, 把下载下来的jar 包上传到hdfs 路径下。
本文jar 包路径,hdfs:///udf/elasticsearch-hadoop-hive-5.6.9.jar
4,哦了,建表,用起来
DELETE jars;
add jar hdfs:///udf/elasticsearch-hadoop-hive-5.6.9.jar;
drop table zebra_info_demo;
CREATE EXTERNAL TABLE zebra_info_demo(
name string,
`type` string,
province double,
city string,
citycode string,
district string,
adcode string,
township string,
business_circle string,
formatted_address string,
location string,
extensions STRUCT<map_lat:double, map_lng:double, avg_price:double, shops:smallint, good_comments:smallint, lvl:smallint, leisure_type:STRING, fun_type:STRING, numbers:smallint>
)
STORED BY ‘org.elasticsearch.hadoop.hive.EsStorageHandler‘
TBLPROPERTIES(‘es.nodes‘ = ‘10.81.179.209:9200‘,
‘es.index.auto.create‘ = ‘false‘,
‘es.resource‘ = ‘zebra_info_demo/zebra_info‘,
‘es.read.metadata‘ = ‘true‘,
‘es.mapping.names‘ = ‘name:name, type:type, province:province, city:city, citycode:citycode, district:district, adcode:adcode, township:township, business_circle:business_circle, formatted_address:formatted_address, location:location, extensions:extensions‘);
5, 往里面填充数据,就O了。
INSERT INTO TABLE zebra_info_demo
SELECT
a.name,
a.brands,
a.province,
a.city,
null as citycode,
null as district,
null as adcode,
null as township,
a.business_circle,
null as formatted_address,
concat(a.map_lat, ‘, ‘, a.map_lng) as `location`,
named_struct(‘map_lat‘, cast(a.map_lat as double), ‘map_lng‘,cast(a.map_lng as double) ,‘avg_price‘, cast(0 as DOUBLE), ‘shops‘, 0S, ‘good_comments‘, 0S, ‘lvl‘, cast(a.lv1 as SMALLINT), ‘leisure_type‘, ‘‘, ‘fun_type‘, ‘‘, ‘numbers‘, 0S) as extentions
from medicalsite_childclinic a;
运行结果:
二,已知elasticsearch 索引,然后,建立hive 表格和elasticsearch 进行交互。可以join 哦,一个字,liubi
1,先看一下索引和数据
已知索引如下:
curl -XPUT ‘10.81.179.209:9200/join_tests?pretty‘ -H ‘Content-Type: application/json‘ -d‘
{
"mappings": {
"cities": {
"properties": {
"province": {
"type": "string"
},
"city": {
"type": "string"
}
}
}
}
}
}
‘
curl -XPUT ‘10.81.179.209:9200/join_tests1?pretty‘ -H ‘Content-Type: application/json‘ -d‘
{
"mappings": {
"shop": {
"properties":{
"name": {
"type": "string"
},
"city": {
"type": "string"
}
}
}
}
}
}
‘
数据如下:
2,建立表格,写一堆有毒的sql 语句。
DELETE jars;
add jar hdfs:///udf/elasticsearch-hadoop-hive-5.6.9.jar;
create table join_tests(
province string,
city string
)STORED BY ‘org.elasticsearch.hadoop.hive.EsStorageHandler‘
TBLPROPERTIES(‘es.nodes‘ = ‘10.81.179.209:9200‘,
‘es.index.auto.create‘ = ‘false‘,
‘es.resource‘ = ‘join_tests/cities‘,
‘es.read.metadata‘ = ‘true‘,
‘es.mapping.names‘ = ‘province:province, city:city‘);
create table join_tests1(
name string,
city string
)STORED BY ‘org.elasticsearch.hadoop.hive.EsStorageHandler‘
TBLPROPERTIES(‘es.nodes‘ = ‘10.81.179.209:9200‘,
‘es.index.auto.create‘ = ‘false‘,
‘es.resource‘ = ‘join_tests1/shop‘,
‘es.read.metadata‘ = ‘true‘,
‘es.mapping.names‘ = ‘name:name, city:city‘);
SELECT
a.province,
b.city,
b.name
from join_tests a LEFT JOIN join_tests1 b on a.city = b.city;
3,运行结果
结束语
推荐一个useful 的工具, apache Hue, 可以用来管理hdfs 文件,hive 操作。mysql 操作等。
原文地址:https://www.cnblogs.com/unnunique/p/9362112.html
时间: 2024-10-10 00:56:19